Classical and Quantum Machine Learning with Tensor Networks

Size: px
Start display at page:

Download "Classical and Quantum Machine Learning with Tensor Networks"

Transcription

1 Classical and Quantum Machine Learning with Tensor Networks E.M. Stoudenmire M INTRIQ

2 Flatiron Institute The mission of the Flatiron Institute is to advance scientific research tough computational methods, including data analysis, modeling and simulation. CCA: Center for Computational Astrophysics CCB: Center for Computational Biology CCQ: Center for Computational Quantum Physics Plus fourth center to be decided

3 Overview Tensor networks = powerful model of many-body wavefunctions Tensor networks can parameterize machine learning models too Resulting learning architecture has interesting capabilities, connections to quantum computing

4 Machine learning galvanizing industry & science Language Processing Self-driving cars Medicine Materials Science / Chemistry

5 Google rebranded a "machine learning first company" Neural nets replace linguistic approach to Google Translate Quantum machine learning

6 Doing tasks thought impossible... Under review as a conference paper at ICLR 2016 U NSUPERVISED R EPRESENTATION L EARNING WITH D EEP C ONVOLUTIONAL G ENERATIVE A DVERSARIAL N ETWORKS Alec Radford & Luke Metz indico Research Vector arithmetic for visual concepts. For each column, the Z vectors of samples are Boston, MA Arithmetic was then performed on the mean vectors creating a new vector Y. The center {alec,luke}@indico.io 7 Jan 2016 Figure 7: averaged. sample on the right hand side is produce by feeding Y as input to the generator. To demonstrate the interpolation capabilities of the generator, uniform noise sampled with scale was added Chintala to Y to produce the Soumith 8 other samples. Applying arithmetic in the input space (bottom two examples) Facebook AI Research results in noisy overlap misalignment. Newdue York,toNY soumith@fb.com Further work is needed to tackle this from of instability. We think that extending this framework A BSTRACT

7 Machine learning has physics in its DNA # " # # " " # " Boltzmann Machines Disordered Ising Model Deep Belief Networks The "Renormalization Group" P. Mehta and D.J. Schwab, arxiv: S. Bradde and W. Bialek, arxiv:

8 Convolutional neural network "MERA" tensor network

9 Are tensor networks useful for machine learning? "MERA" tensor network Tensor networks can represent weights of useful and interesting machine learning models Realized benefits: Linear scaling Adaptive weights Learning data "features" Future benefits? Interpretability / theory Better algorithms Quantum computing

10 What is machine learning?

11 What is machine learning? Data driven problem solving Any system that, given more data, performs increasingly better at some task Framework / philosophy, not single method

12 Goal: train model f(x) mapping input x to target f(x) 1 0 "dog"

13 Goal: train model f(x) mapping input x to target f(x) 0 1 "cat"

14 Philosophy of Machine Learning Map from images to labels is just a function Parameterize a set of very flexible functions (prefer convenient functions over "correct" ones) Prevent overfitting by regularization (prefer simple functions) = training data

15 Philosophy of Machine Learning Map from images to labels is just a function Parameterize a set of very flexible functions (prefer convenient functions over "correct" ones) Prevent overfitting by regularization (prefer simple functions) = training data = testing data

16 Supervised Learning Given labeled training data (labels A and B) Find decision function f(x) > 0 f(x) < 0 f(x) x 2 A x 2 B Example: identify photos of alligators and bears

17 Unsupervised Learning Given unlabeled training data {x j } Find function Find function f(x) such that f(x j ) ' p(x j ) f(x) such that f(x j ) 2 ' p(x j ) Find data clusters and which data belongs to each cluster Discover reduced representations of data for other learning tasks (e.g. supervised)

18 What are Tensor Networks?

19 Original setting is quantum mechanics Spin model (transverse field Ising model): z z h x Ĥ = X j ( z j z j+1 h x j ) " " " " " " " h<<1 " " " " " " "h>>1

20 Wavefunction just a rule to map spin configurations to numbers s 1 s 2 s 3 s 4 s 5 s 6 s 7 s 8 " # " " " " " " " # " " " " " " " # " # " " " " " " " " # " # " " # " # " " " " " " " " # " # " " # # # # " " " " # # # # " " " Simplest rule: store every amplitude separately

21 [ Let's make a different rule Introduce matrices, one for each spin " M " = [ # M # = [ [ Östlund, Rommer, Phys. Rev. Lett. 75, 3537 (1995)

22 Compute wavefunction by multiplying matrices together " # " " # M " 1 M # 2 M " 3 M " 4 M # 5 " " # # # M " 1 M " 2 M # 3 M # 4 M # 5 " # # " " M " 1 M # 2 M # 3 M " 4 M " 5

23 This rule is called a matrix product state (MPS) s 1 s 2 s 3 s 4 s 5 = M s 1 1 M s 2 2 M s 3 3 M s 4 4 M s 5 5 Size of matrices called m (the "bond dimension") For m = 2 N/2 can represent any state of N spins Just a w to compress a big tensor Represents 2 N amplitudes using only (2 N m 2 ) parameters

24 Tensor Diagrams

25 Helpful to draw N-index tensor as blob with N lines s 1 s 2 s 3 s 4 s N s 1 s 2 s 3 s N = No symmetries or transformation properties assumed

26 Diagrams for simple tensors j v j i j M ij i j k T ijk

27 Joining lines implies contraction, can omit names X i j j M ij v j A ij B jk = AB A ij B ji =Tr[AB]

28 Matrix product state in diagram notation s 1 s 2 s 3 s 4 s 5 s 6 = X M s 1 1 M s M s M s M s M s 6 5 s 1 s 2 s 3 s 4 s 5 s 6 = Can suppress index names, very convenient

29 Matrix product state in diagram notation s 1 s 2 s 3 s 4 s 5 s 6 = X M s 1 1 M s M s M s M s M s 6 5 s 1 s 2 s 3 s 4 s 5 s 6 = Can suppress index names, very convenient

30 Matrix product state in diagram notation s 1 s 2 s 3 s 4 s 5 s 6 = X M s 1 1 M s M s M s M s M s 6 5 = Can suppress index names, very convenient

31 Besides MPS, other successful tensor are PEPS and MERA PEPS (2D systems) MERA (critical systems) Evenbly, Vidal, PRB 79, (2009) Verstraete, Cirac, cond-mat/ (2004) Orus, Ann. Phys. 349, 117 (2014)

32 Tensor Network Machine Learning David Schwab Stoudenmire, Schwab, Advanced in Neural Information Processing Systems (NIPS), 29, 4799 [arxiv: ]

33 Raw data vectors x =(x 1,x 2,x 3,...,x N ) Example: grscale images, components of x are pixels x j 2 [0, 1]

34 Propose following model f(x) =W (x) = X s W s1 s 2 s 3 s N x s 1 1 xs 2 2 xs 3 3 xs N N s j =0, 1 Weights are N-index tensor Like N-site wavefunction Novikov, Trofimov, Oseledets, arxiv:

35 N=3 example: f(x) =W (x) = X s W s1 s 2 s x s xs 2 2 xs 3 3 = W W 100 x 1 + W 010 x 2 + W 001 x 3 + W 110 x 1 x 2 + W 101 x 1 x 3 + W 011 x 2 x 3 + W 111 x 1 x 2 x 3 Contains linear classifier, plus other "feature maps"

36 More generally, apply local "feature maps" s j (x j ) f(x) =W (x) = X s W s1 s 2 s 3 s N s 1 (x 1 ) s 2 (x 2 ) s 3 (x 3 ) s N (x N ) Highly expressive! Cohen et al. arxiv: Novikov, Trofimov, Oseledets, arxiv: Stoudenmire, Schwab, arxiv:

37 x = input For example, following local feature map (x j )= h cos 2 x j i, sin 2 x j x j 2 [0, 1] Picturesque idea of pixels as "spins" or "qubits"

38 x = input = local feature map Total feature map (x) s 1 s 2 s N (x) = s 1 (x 1 ) s 2 (x 2 ) s N (x N ) Tensor product of local feature maps / vectors Just like product state wavefunction of spins Vector in dimensional space 2 N

39 x = input = local feature map Total feature map (x) More detailed notation x =[x 1, x 2, x 3,..., x N ] raw inputs (x) = [ 1( x 1 ) 2( x 1 ) [ [ 1( x 2 ) 2( x 2 ) [ [ 1( x 3 ) 2( x 3 ) [ [ 1( x N )... feature 2( x N ) [ vector

40 x = input = local feature map Total feature map (x) Tensor diagram notation x =[x 1, x 2, x 3,..., x N ] raw inputs (x) = s 1 s 2 s 3 s 4 s 5 s 6 s 1 s 2 s 3 s 4 s 5 s 6 s N s N feature vector

41 Construct decision function f(x) =W (x) (x)

42 Construct decision function f(x) =W (x) W (x)

43 Construct decision function f(x) =W (x) f(x) = W (x) W =

44 Main approximation W = order-n tensor matrix product state (MPS)

45 ) Main approximation W = order-n tensor matrix product state (MPS) PEPS )

46 Can use algorithm similar to DMRG to optimize Number of parameters is adaptive Scaling is N N T m 3 N = size of input N T = size of training set m = MPS bond dimension f(x) = W (x)

47 Can use algorithm similar to DMRG to optimize Number of parameters is adaptive Scaling is N N T m 3 N = size of input N T = size of training set m = MPS bond dimension f(x) = W (x)

48 Can use algorithm similar to DMRG to optimize Number of parameters is adaptive Scaling is N N T m 3 N = size of input N T = size of training set m = MPS bond dimension f(x) = W (x)

49 Can use algorithm similar to DMRG to optimize Number of parameters is adaptive Scaling is N N T m 3 N = size of input N T = size of training set m = MPS bond dimension f(x) = W (x)

50 Can use algorithm similar to DMRG to optimize Number of parameters is adaptive Scaling is N N T m 3 N = size of input N T = size of training set m = MPS bond dimension f(x) = W (x)

51 Can use algorithm similar to DMRG to optimize Number of parameters is adaptive Scaling is N N T m 3 N = size of input N T = size of training set m = MPS bond dimension f(x) = W (x)

52 [ Why should this work at all? Linear classifier f(x) =V x exactly m=2 MPS W = [ V 0 1 [ [ [ ˆ1 0 ˆV 1 ˆ1 [ [ ˆ1 0 ˆV 2 ˆ1 [ ˆ1 0 ˆV3 ˆ1 ˆ1 = [1 0] f(x) =W (x) ˆV j =[0 V j ] s j (x j )=[1,x j ] Novikov, Trofimov, Oseledets, arxiv:

53 Experiment: handwriting classification (MNIST) Train to 99.95% accuracy on 60,000 training images Obtain 99.03% accuracy on 10,000 test images (only 97 incorrect) Stoudenmire, Schwab, arxiv:

54 Tensor Network Machine Learning Studies

55 Deep Learning and Quantum Entanglement... Yoav Levine, David Yakira, Nadav Cohen, Amnon Shashua (arxiv: ) "ConvAC" deep neural net = tree tensor network Tensor network rank as capacity of model Experiment on "inductive bias" of model architecture Tree Network as a Deep Neural Net Inductive Bias Experiment

56 <latexit sha1_base64="otslswa9of52bfz3egobgoif5fw=">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</latexit> <latexit sha1_base64="fedyokfdb3cbigr2ojh8qjo2ugy=">aaacuhicdvfnswmxee3x7/qtry/brfbudougiojgxaoivag7lnl0uoym2sxjqmxtt/cqv/+w/8z07ufthqg83ryxn8kkuedgbsfnzzuznztfwfyql6+srq1vbg7dmqzqdfsse5m+t8cg4apbllub97lgkinau6r/purfpai2pfm3dpbjlcfvvmczweddp3fczoyfnikq6cqix8an47rsbny+om7gconkmghgtmmgt3ej2nimcfipcom5sd6k2hzqguqtl9wsq7rnmc7tzdodzwnf/nsuii0zymqpjdgh87c3iqf12oxthculv3lhubhvof4m3o6og0yzuykwyoanpczurza2hg1n1ppvl4xdipqxxlqi922a7jmkjlco2jrplfdymnknuphp5wjxom1jgoph74mkvdxd+caqdo4tfpp0nwmp6x5iw/xg6n4d8ntojws3hcck4o/lpt8xixyq7zjfskjifkjfyqs9iijktklbyrd+/eay/1+lfuq4092+rxefolzehcvq==</latexit> <latexit sha1_base64="fedyokfdb3cbigr2ojh8qjo2ugy=">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</latexit> <latexit sha1_base64="w0a/nhsg5s1nlxqwd+he2qxfls0=">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</latexit> <latexit sha1_base64="w0a/nhsg5s1nlxqwd+he2qxfls0=">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</latexit> <latexit sha1_base64="a9ukl/2cncmdla+qucrbfwdp0gq=">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</latexit> <latexit sha1_base64="a9ukl/2cncmdla+qucrbfwdp0gq=">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</latexit> <latexit sha1_base64="0hczlpdj61quhd03ptcbjhyacqq=">aaacuhicdvfnswmxee3x7/qtry/brfbudougiojgxaoivag7lnl0uoym2sxjqmxtt/cqv/+w/8z07ufthqg83ryxn8kkuedgbsfnzzuznztfwfyql6+srq1vbg7dmqzqdfsse5m+t8cg4apbllub97lgkinau6r/purfpai2pfm3dpbjlcfvvmczweddp3cooht+0aiqopmghaofjouys1n7ilozkyqqywqy0w6d3mylamuzwge9kgzmwpqqyttbbrjnxfazdumey7q0l2l3lkuv+9nrgjrmibonlgafzn/eijzwaxe2dxsxxowfrcw+g3qfodajo4ftltfirbg4aexznytld6cbwfc99ujhe8ukbnutoz7aytumywivktsossoxp4w0qnq9cphbnwiyueeikvrhyxr1dx1zqoe6h9+k/ytby/pfkjp+clmdhn83oalazczxi7g68m9ox8tdjdtkl+ytkbysm3jblkmlmjksv/jg3r0td7zu499srzb2bjnf5ekvbnfcwa==</latexit> <latexit sha1_base64="0hczlpdj61quhd03ptcbjhyacqq=">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</latexit> <latexit sha1_base64="a6i0k65urn1/5yzqit3xf7chcei=">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</latexit> <latexit sha1_base64="a6i0k65urn1/5yzqit3xf7chcei=">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</latexit> <latexit sha1_base64="kfwcwg5sm1d4ghdfuysrs3ymofw=">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</latexit> <latexit sha1_base64="kfwcwg5sm1d4ghdfuysrs3ymofw=">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</latexit> <latexit sha1_base64="kfwcwg5sm1d4ghdfuysrs3ymofw=">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</latexit> 2<latexit sha1_base64="a611a2ayksyyekr8vjuywel0bmw=">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</latexit> Unsupervised Generative Modeling ing MPS Zhao-Yu Han, Jun Wang, Heng Fan, Lei Wang, Pan Zhang (arxiv: ) Map data to product state, tensor network weights Squared output is probability "Born machine" "Perfect" sampling (no autocorrelation) x<latexit sha1_base64="fedyokfdb3cbigr2ojh8qjo2ugy=">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</latexit> 1 x<latexit sha1_base64="w0a/nhsg5s1nlxqwd+he2qxfls0=">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</latexit> 2 x<latexit sha1_base64="a9ukl/2cncmdla+qucrbfwdp0gq=">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</latexit> 3 x<latexit sha1_base64="0hczlpdj61quhd03ptcbjhyacqq=">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</latexit> 4 x<latexit sha1_base64="a6i0k65urn1/5yzqit3xf7chcei=">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</latexit> 5 x 6 p(x) = L ln( T ) D max Negative Log-Likelihood (d) row reconstruction on testing Reconstructing Testing Images

57 )). Compared with Refs. (Stoudenmire & Schwab, 2016; Han et al., 2017) where a onel (1D) TN (called matrix product state (MPS) (O stlund & Rommer, 1995)) is used, TTN he two-dimensional (2D) nature of images. The algorithm is inspired by the multipartite nt renormalization ansatz (MERA) approach (Vidal, 2007; 2008; Cincio et al., 2008; Vidal,Ding 2009),Liu, where the tensors the TN Wittek, are kept tocheng be unitary duringraul the training. We Garcia, Gang Su, Maciej Lewenstein Shi-Ju Ran,in Peter Peng, Blazquez orithm on both the MNIST (handwriting recognition with binary images) and CIFAR (arxiv: ) n of color images) databases and obtain accuracies comparable to the performance of al neural networks. More importantly, the TN states can then be defined that optimally ch class of images as a quantum many-body state, which is akin to the study of a duality obabilistic graphical modelslearning and TNs (Robeva Seigal,tensor 2017). Wenetworks contrast the bond Supervised with&tree and model complexity, with results indicating that a growing bond dimension overfits the udy the representation in the different lers in the hierarchical TN with t-sne (Van der Tests on MNIST, CIFAR-10 Hinton, 2008), and find that the level of abstraction changes the same w as in a deep al neural network (Krizhevsky et al., 2012) or a deep belief network (Hinton et al., 2006), Under review as a conference paper at ICLR 2018 Studied properties of the trained model (feature entanglement) hest level of the hierarchy allows for a clear separation of the classes. Finally, we showrepresentations, lities between each two TN states from the two different image classes are low, and we e entanglement entropy of each TN state, which gives an indication of the difficulty of Machine Learning By Hierarchical Tensor Networks... (b) (c) (a) (b) (c) (d) (e) (f) (d) Figure 3: Embedding of data instances of CIFAR-10 by t-sne corresponding to each ler in the TTN: (a) original data distribution and (b) the 1st, (c) 2nd, (d) 3rd, (e) 4th, and (f) 5th ler. Color online) The left figure (a) shows the configuration of TTN. The squares at the esent the vectors obtainedmodel from thearchitecture pixels of one image tough the feature map. The Data Representation at B ENCHMARK ON CIFAR-10 e top represents the label. The right figures are (b) the illustrations of 4.1 the environment Different Scales To verify the representation power of TTNs, we used the CIFAR-10 dataset (Krizhevsky & Hinton, he schematic diagram of fidelity and (d) entanglement entropy calculation. 2009). The dataset consists of 60, RGB images in 10 classes, with 6,000 instances per class. There are 50,000 training images and 10,000 test images. Each RGB image was originally pixels: we transformed them to grscale. Working with gr-scale images reduced the complexity of training, with the trade-off being that less information was available for learning.

58 Learning Relevant Features of Data... E.M. Stoudenmire (Quant. Sci. Tech. 3, [2018]) Unsupervised determination of tree tensor network (compress data) Supervised training of top ler Excellent performance with "features" determined by tree tensors supervised top ler unsupervised tree data input µ = (1 µ) X j + µ 89% accuracy on Fashion MNIST data set mixed training supervised / unsupervised

59 Quantum Machine Learning with Tensor Networks Bill Huggins Huggins, Patil, Whaley, Stoudenmire, arxiv: Grant, Benedetti, et al., arxiv:

60 Two recent proposals for machine learning with a quantum computer 1. supervised / discriminative Farhi, Neven, arxiv: Schuld, Killoran, arxiv:

61 Two recent proposals for machine learning with a quantum computer 1. supervised / discriminative x! Farhi, Neven, arxiv: Schuld, Killoran, arxiv:

62 Two recent proposals for machine learning with a quantum computer 1. supervised / discriminative U D x! Farhi, Neven, arxiv: Schuld, Killoran, arxiv:

63 Two recent proposals for machine learning with a quantum computer 1. supervised / discriminative U D x!! 0, 1 Farhi, Neven, arxiv: Schuld, Killoran, arxiv:

64 Two recent proposals for machine learning with a quantum computer 2. unsupervised / generative Gao, Zhang, Duan, arxiv: Benedetti, Garcia-Pintos, Nam, Perdomo-Ortiz, arxiv:

65 Two recent proposals for machine learning with a quantum computer 2. unsupervised / generative Gao, Zhang, Duan, arxiv: Benedetti, Garcia-Pintos, Nam, Perdomo-Ortiz, arxiv:

66 Two recent proposals for machine learning with a quantum computer 2. unsupervised / generative U G Gao, Zhang, Duan, arxiv: Benedetti, Garcia-Pintos, Nam, Perdomo-Ortiz, arxiv:

67 <latexit sha1_base64="2nihmcpuqnasfc+yvksjsqjzf+8=">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</latexit> <latexit sha1_base64="2nihmcpuqnasfc+yvksjsqjzf+8=">aaacznicdvhlattafb0rfatuy0mhm26gikjxrmmc7tkqtzco1enaeuzqfcupnhmjmzfti4tu+xml2/sh+jcdkv4ksxnh4hduoxnfasmfdvh0rxccphn67pnhi/7lv6/fvb0chv/yojicj7yqhblkwaiugidooilxpufqqctldhnw5i9xakwo9he3ljfrkgurcq7ou7pb+9iifohamokaxgrcis3qh81seebdqau6c9gwhgqb49lr73c8l3iludsuwdopi0qx1gcc4bkbflxzlievicephxou2qtubmjoj8/mavyy/7sjhxvxuyoydq1sr2xbta9zlbkvn61c9jwphs4rh5rffsoqsv1b223qutdinvx7anwi3yvlczdand9zp9z4zqulqm/reimumbkkjlhbymbbq96eldagcz9gc1+dgthrx7kthmyzr919p9pron4rjugjlwcvp1bjg++4/e3zwwvugovrkevddn4snp5tr3tippcp5dnh5as5jd/imewijxvyh9yqv8e4wavn8pnwgvs2nnfkxgs//gosyevx</latexit> <latexit sha1_base64="2nihmcpuqnasfc+yvksjsqjzf+8=">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</latexit> <latexit sha1_base64="2nihmcpuqnasfc+yvksjsqjzf+8=">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</latexit> Two recent proposals for machine learning with a quantum computer 2. unsupervised / generative U G! x Gao, Zhang, Duan, arxiv: Benedetti, Garcia-Pintos, Nam, Perdomo-Ortiz, arxiv:

68 <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">aaacuxicdvhbthsxehw2ldbakbthxqyukd6wgjpf6q4najiizeyq6iwweymbg9k9ipz8atf22t/ib3cwhahjrrl09oy9v7enlaswloqeg8ghj5+2tnc+n3f3vux/ptj8dmvz0nds8fzmppecrsk0dpxwenufqvcpxg46uzj3u/dormj1hzctmfgqateshjynbjqdy8fbglwiuugqyasqkkvddq4b/+nhzkuf2nej1vzzvlikaumelzxqxfavgemux7qeghtap61hk98syqjnljj3a0zt86kldwtlxqlqrc2l7vzcl1vx7prmdjjxrrott8nwhusupyon84hqqd3mmpb8cn8lnspgyd3pnvacyah3iufohu/qzfosqwlutjq4z6oeqxyb0jl/4gxznrpyuceylobscy26vr691kc9i2ztdulwn21k8sy3lr9t9n6dq+c23wjri12fhocxi+3ukb/kjzkmjjysc/kbxjeo4sqjt+qv+rf8ciayb3ev0qcx8hwnsxxyfyrp3hc=</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">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</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">aaacuxicdvhbthsxehw2ldbakbthxqyukd6wgjpf6q4najiizeyq6iwweymbg9k9ipz8atf22t/ib3cwhahjrrl09oy9v7enlaswloqeg8ghj5+2tnc+n3f3vux/ptj8dmvz0nds8fzmppecrsk0dpxwenufqvcpxg46uzj3u/dormj1hzctmfgqateshjynbjqdy8fbglwiuugqyasqkkvddq4b/+nhzkuf2nej1vzzvlikaumelzxqxfavgemux7qeghtap61hk98syqjnljj3a0zt86kldwtlxqlqrc2l7vzcl1vx7prmdjjxrrott8nwhusupyon84hqqd3mmpb8cn8lnspgyd3pnvacyah3iufohu/qzfosqwlutjq4z6oeqxyb0jl/4gxznrpyuceylobscy26vr691kc9i2ztdulwn21k8sy3lr9t9n6dq+c23wjri12fhocxi+3ukb/kjzkmjjysc/kbxjeo4sqjt+qv+rf8ciayb3ev0qcx8hwnsxxyfyrp3hc=</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> Two issues with these proposals U D U G discriminative generative

69 <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">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</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">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</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">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</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">aaacuxicdvhbthsxehw2ldbakbthxqyukd6wgjpf6q4najiizeyq6iwweymbg9k9ipz8atf22t/ib3cwhahjrrl09oy9v7enlaswloqeg8ghj5+2tnc+n3f3vux/ptj8dmvz0nds8fzmppecrsk0dpxwenufqvcpxg46uzj3u/dormj1hzctmfgqateshjynbjqdy8fbglwiuugqyasqkkvddq4b/+nhzkuf2nej1vzzvlikaumelzxqxfavgemux7qeghtap61hk98syqjnljj3a0zt86kldwtlxqlqrc2l7vzcl1vx7prmdjjxrrott8nwhusupyon84hqqd3mmpb8cn8lnspgyd3pnvacyah3iufohu/qzfosqwlutjq4z6oeqxyb0jl/4gxznrpyuceylobscy26vr691kc9i2ztdulwn21k8sy3lr9t9n6dq+c23wjri12fhocxi+3ukb/kjzkmjjysc/kbxjeo4sqjt+qv+rf8ciayb3ev0qcx8hwnsxxyfyrp3hc=</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> Two issues with these proposals U D U G discriminative generative 1. efficient parameterization of N-qubit circuit? (vanishing gradient?*) * McClean, Boixo, et al., arxiv:

70 <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">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</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">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</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">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</latexit> <latexit sha1_base64="9jlyt9okhwteknw/5amnrwlzqic=">aaacuxicdvhbthsxehw2ldbakbthxqyukd6wgjpf6q4najiizeyq6iwweymbg9k9ipz8atf22t/ib3cwhahjrrl09oy9v7enlaswloqeg8ghj5+2tnc+n3f3vux/ptj8dmvz0nds8fzmppecrsk0dpxwenufqvcpxg46uzj3u/dormj1hzctmfgqateshjynbjqdy8fbglwiuugqyasqkkvddq4b/+nhzkuf2nej1vzzvlikaumelzxqxfavgemux7qeghtap61hk98syqjnljj3a0zt86kldwtlxqlqrc2l7vzcl1vx7prmdjjxrrott8nwhusupyon84hqqd3mmpb8cn8lnspgyd3pnvacyah3iufohu/qzfosqwlutjq4z6oeqxyb0jl/4gxznrpyuceylobscy26vr691kc9i2ztdulwn21k8sy3lr9t9n6dq+c23wjri12fhocxi+3ukb/kjzkmjjysc/kbxjeo4sqjt+qv+rf8ciayb3ev0qcx8hwnsxxyfyrp3hc=</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> <latexit sha1_base64="pxscfmw4nvyexrqeqsh7vzqgrdw=">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</latexit> Two issues with these proposals U D U G discriminative generative 1. efficient parameterization of N-qubit circuit? (vanishing gradient?*) 2. require too many qubits for realistic data sizes * McClean, Boixo, et al., arxiv:

71 D =4 <latexit sha1_base64="jfp3kcp4tz8dri6gelidalutbak=">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</latexit> <latexit sha1_base64="jfp3kcp4tz8dri6gelidalutbak=">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</latexit> <latexit sha1_base64="jfp3kcp4tz8dri6gelidalutbak=">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</latexit> h0 yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t h0 yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t h0 yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t h0 yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t h0 yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t h0 yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t h0 yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t h0 yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t yz EE AP Qm 45 lq rm =I >" AA CA Hv ci Vd LH AN JF G3 3d r3 s0 g1 FE Vy Ap qj NG ws rv Sh Ib fz 2S pd Zm Jh Jl cp 8R Fh dv F+ +v dj dh 6p ey wb j7 zl 0X uk Lu N8 wn Xa ll Wd 51 rr 5G bt z2 7u /e mc zk DT sd Et hp S8 CM 4i ow l7 DB kf ri bc Fp Te Hf Ee v2 MB d3 xl rj EG eo DI sz 6A ls sg gq te xz 1g QZ F0 R4 4T BZ 3o 7j Nu 6j fi ik ks Ay bm w0 Gy c1 rg ca WU we Cb HE Os pk ob r4 ul 6t HJ uj Tn aq db 5U Wb E7 H9 dc YK cy ou 9J nm z9 3E ej lr Yf Vw cl pc XU 7X jl oq LB ZU Qn Px 1+ jw 2s DA ND ax U+ GE tz K2 pm CH 5Z JZ fp ir an Gf YZ KT no ct Xo 4P 0w Kq be Ps tq md cu UU ie vl xy 1x X/ 71 or 6E 9h m+ 1/ CS f0 /C 47 +w vg 96 C4 oz Ft nv er 2D Lx 8+ hm 35 Rl Qy 3Q MJ nq KJ 1k Su de kw Kh sx bk fe uc PP SR 3T L5 cv Ub 0s +9 Th 6f va II j3 =M /< al et ix >t =<latexit sha1_base64="ufbkrtbq720kdpn34ecddtho5ne=">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</latexit> <latexit sha1_base64="ufbkrtbq720kdpn34ecddtho5ne=">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</latexit> <latexit sha1_base64="ufbkrtbq720kdpn34ecddtho5ne=">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</latexit> Tensor networks are equivalent to quantum circuits

72 Quantum circuit for matrix product state (m = 4) =

73 Quantum circuit for matrix product state (m = 4) =

74 <latexit sha1_base64="2nihmcpuqnasfc+yvksjsqjzf+8=">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</latexit> <latexit sha1_base64="2nihmcpuqnasfc+yvksjsqjzf+8=">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</latexit> <latexit sha1_base64="2nihmcpuqnasfc+yvksjsqjzf+8=">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</latexit> <latexit sha1_base64="2nihmcpuqnasfc+yvksjsqjzf+8=">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</latexit> Suggests MPS parameterization of generative quantum model! x much fewer paramaters than arbitrary circuit can initialize with classically optimized MPS

75 Discriminative model basically the reverse

76 Test discriminative idea, using only operations available to quantum hardware: Bill Huggins 8x8 images (MNIST) distinguish 0's from 1's Obtain 99% accuracy training & test

Machine Learning with Tensor Networks

Machine Learning with Tensor Networks Machine Learning with Tensor Networks E.M. Stoudenmire and David J. Schwab Advances in Neural Information Processing 29 arxiv:1605.05775 Beijing Jun 2017 Machine learning has physics in its DNA # " # #

More information

Machine Learning with Quantum-Inspired Tensor Networks

Machine Learning with Quantum-Inspired Tensor Networks Machine Learning with Quantum-Inspired Tensor Networks E.M. Stoudenmire and David J. Schwab Advances in Neural Information Processing 29 arxiv:1605.05775 RIKEN AICS - Mar 2017 Collaboration with David

More information

Tensor network vs Machine learning. Song Cheng ( 程嵩 ) IOP, CAS

Tensor network vs Machine learning. Song Cheng ( 程嵩 ) IOP, CAS Tensor network vs Machine learning Song Cheng ( 程嵩 ) IOP, CAS physichengsong@iphy.ac.cn Outline Tensor network in a nutshell TN concepts in machine learning TN methods in machine learning Outline Tensor

More information

Quantum Convolutional Neural Networks

Quantum Convolutional Neural Networks Quantum Convolutional Neural Networks Iris Cong Soonwon Choi Mikhail D. Lukin arxiv:1810.03787 Berkeley Quantum Information Seminar October 16 th, 2018 Why quantum machine learning? Machine learning: interpret

More information

Opportunities and challenges in quantum-enhanced machine learning in near-term quantum computers

Opportunities and challenges in quantum-enhanced machine learning in near-term quantum computers Opportunities and challenges in quantum-enhanced machine learning in near-term quantum computers Alejandro Perdomo-Ortiz Senior Research Scientist, Quantum AI Lab. at NASA Ames Research Center and at the

More information

Parts Manual. EPIC II Critical Care Bed REF 2031

Parts Manual. EPIC II Critical Care Bed REF 2031 EPIC II Critical Care Bed REF 2031 Parts Manual For parts or technical assistance call: USA: 1-800-327-0770 2013/05 B.0 2031-109-006 REV B www.stryker.com Table of Contents English Product Labels... 4

More information

i;\-'i frz q > R>? >tr E*+ [S I z> N g> F 'x sa :r> >,9 T F >= = = I Y E H H>tr iir- g-i I * s I!,i --' - = a trx - H tnz rqx o >.F g< s Ire tr () -s

i;\-'i frz q > R>? >tr E*+ [S I z> N g> F 'x sa :r> >,9 T F >= = = I Y E H H>tr iir- g-i I * s I!,i --' - = a trx - H tnz rqx o >.F g< s Ire tr () -s 5 C /? >9 T > ; '. ; J ' ' J. \ ;\' \.> ). L; c\ u ( (J ) \ 1 ) : C ) (... >\ > 9 e!) T C). '1!\ /_ \ '\ ' > 9 C > 9.' \( T Z > 9 > 5 P + 9 9 ) :> : + (. \ z : ) z cf C : u 9 ( :!z! Z c (! $ f 1 :.1 f.

More information

Introduction to tensor network state -- concept and algorithm. Z. Y. Xie ( 谢志远 ) ITP, Beijing

Introduction to tensor network state -- concept and algorithm. Z. Y. Xie ( 谢志远 ) ITP, Beijing Introduction to tensor network state -- concept and algorithm Z. Y. Xie ( 谢志远 ) 2018.10.29 ITP, Beijing Outline Illusion of complexity of Hilbert space Matrix product state (MPS) as lowly-entangled state

More information

arxiv: v2 [cs.lg] 10 Apr 2017

arxiv: v2 [cs.lg] 10 Apr 2017 Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design arxiv:1704.01552v2 [cs.lg] 10 Apr 2017 Yoav Levine David Yakira Nadav Cohen Amnon Shashua The Hebrew

More information

Supervised Learning with Tensor Networks

Supervised Learning with Tensor Networks Supervised Learning with Tensor Networks E. M. Stoudenmire Perimeter Institute for Theoretical Physics Waterloo, Ontario, N2L 2Y5, Canada David J. Schwab Department of Physics Northwestern University,

More information

A Video from Google DeepMind.

A Video from Google DeepMind. A Video from Google DeepMind http://www.nature.com/nature/journal/v518/n7540/fig_tab/nature14236_sv2.html Can machine learning teach us cluster updates? Lei Wang Institute of Physics, CAS https://wangleiphy.github.io

More information

A L A BA M A L A W R E V IE W

A L A BA M A L A W R E V IE W A L A BA M A L A W R E V IE W Volume 52 Fall 2000 Number 1 B E F O R E D I S A B I L I T Y C I V I L R I G HT S : C I V I L W A R P E N S I O N S A N D TH E P O L I T I C S O F D I S A B I L I T Y I N

More information

Understanding Deep Learning via Physics:

Understanding Deep Learning via Physics: Understanding Deep Learning via Physics: The use of Quantum Entanglement for studying the Inductive Bias of Convolutional Networks Nadav Cohen Institute for Advanced Study Symposium on Physics and Machine

More information

IPAM/UCLA, Sat 24 th Jan Numerical Approaches to Quantum Many-Body Systems. QS2009 tutorials. lecture: Tensor Networks.

IPAM/UCLA, Sat 24 th Jan Numerical Approaches to Quantum Many-Body Systems. QS2009 tutorials. lecture: Tensor Networks. IPAM/UCLA, Sat 24 th Jan 2009 umerical Approaches to Quantum Many-Body Systems QS2009 tutorials lecture: Tensor etworks Guifre Vidal Outline Tensor etworks Computation of expected values Optimization of

More information

Expressive Efficiency and Inductive Bias of Convolutional Networks:

Expressive Efficiency and Inductive Bias of Convolutional Networks: Expressive Efficiency and Inductive Bias of Convolutional Networks: Analysis & Design via Hierarchical Tensor Decompositions Nadav Cohen The Hebrew University of Jerusalem AAAI Spring Symposium Series

More information

Expressive Efficiency and Inductive Bias of Convolutional Networks:

Expressive Efficiency and Inductive Bias of Convolutional Networks: Expressive Efficiency and Inductive Bias of Convolutional Networks: Analysis & Design via Hierarchical Tensor Decompositions Nadav Cohen The Hebrew University of Jerusalem AAAI Spring Symposium Series

More information

Neural Network Representation of Tensor Network and Chiral States

Neural Network Representation of Tensor Network and Chiral States Neural Network Representation of Tensor Network and Chiral States Yichen Huang ( 黄溢辰 ) 1 and Joel E. Moore 2 1 Institute for Quantum Information and Matter California Institute of Technology 2 Department

More information

Accelerated Monte Carlo simulations with restricted Boltzmann machines

Accelerated Monte Carlo simulations with restricted Boltzmann machines Accelerated simulations with restricted Boltzmann machines Li Huang 1 Lei Wang 2 1 China Academy of Engineering Physics 2 Institute of Physics, Chinese Academy of Sciences July 6, 2017 Machine Learning

More information

176 5 t h Fl oo r. 337 P o ly me r Ma te ri al s

176 5 t h Fl oo r. 337 P o ly me r Ma te ri al s A g la di ou s F. L. 462 E l ec tr on ic D ev el op me nt A i ng er A.W.S. 371 C. A. M. A l ex an de r 236 A d mi ni st ra ti on R. H. (M rs ) A n dr ew s P. V. 326 O p ti ca l Tr an sm is si on A p ps

More information

SGD and Deep Learning

SGD and Deep Learning SGD and Deep Learning Subgradients Lets make the gradient cheating more formal. Recall that the gradient is the slope of the tangent. f(w 1 )+rf(w 1 ) (w w 1 ) Non differentiable case? w 1 Subgradients

More information

ECE 521. Lecture 11 (not on midterm material) 13 February K-means clustering, Dimensionality reduction

ECE 521. Lecture 11 (not on midterm material) 13 February K-means clustering, Dimensionality reduction ECE 521 Lecture 11 (not on midterm material) 13 February 2017 K-means clustering, Dimensionality reduction With thanks to Ruslan Salakhutdinov for an earlier version of the slides Overview K-means clustering

More information

10-810: Advanced Algorithms and Models for Computational Biology. Optimal leaf ordering and classification

10-810: Advanced Algorithms and Models for Computational Biology. Optimal leaf ordering and classification 10-810: Advanced Algorithms and Models for Computational Biology Optimal leaf ordering and classification Hierarchical clustering As we mentioned, its one of the most popular methods for clustering gene

More information

T h e C S E T I P r o j e c t

T h e C S E T I P r o j e c t T h e P r o j e c t T H E P R O J E C T T A B L E O F C O N T E N T S A r t i c l e P a g e C o m p r e h e n s i v e A s s es s m e n t o f t h e U F O / E T I P h e n o m e n o n M a y 1 9 9 1 1 E T

More information

T ensor N et works. I ztok Pizorn Frank Verstraete. University of Vienna M ichigan Quantum Summer School

T ensor N et works. I ztok Pizorn Frank Verstraete. University of Vienna M ichigan Quantum Summer School T ensor N et works I ztok Pizorn Frank Verstraete University of Vienna 2010 M ichigan Quantum Summer School Matrix product states (MPS) Introduction to matrix product states Ground states of finite systems

More information

Neural Networks and Deep Learning

Neural Networks and Deep Learning Neural Networks and Deep Learning Professor Ameet Talwalkar November 12, 2015 Professor Ameet Talwalkar Neural Networks and Deep Learning November 12, 2015 1 / 16 Outline 1 Review of last lecture AdaBoost

More information

Holographic Geometries from Tensor Network States

Holographic Geometries from Tensor Network States Holographic Geometries from Tensor Network States J. Molina-Vilaplana 1 1 Universidad Politécnica de Cartagena Perspectives on Quantum Many-Body Entanglement, Mainz, Sep 2013 1 Introduction & Motivation

More information

STA 414/2104: Lecture 8

STA 414/2104: Lecture 8 STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable models Background PCA

More information

UNSUPERVISED LEARNING

UNSUPERVISED LEARNING UNSUPERVISED LEARNING Topics Layer-wise (unsupervised) pre-training Restricted Boltzmann Machines Auto-encoders LAYER-WISE (UNSUPERVISED) PRE-TRAINING Breakthrough in 2006 Layer-wise (unsupervised) pre-training

More information

THE TRANSLATION PLANES OF ORDER 49 AND THEIR AUTOMORPHISM GROUPS

THE TRANSLATION PLANES OF ORDER 49 AND THEIR AUTOMORPHISM GROUPS MATHEMATICS OF COMPUTATION Volume 67, Number 223, July 1998, Pages 1207 1224 S 0025-5718(98)00961-2 THE TRANSLATION PLANES OF ORDER 49 AND THEIR AUTOMORPHISM GROUPS C. CHARNES AND U. DEMPWOLFF Abstract.

More information

Deep Feedforward Networks

Deep Feedforward Networks Deep Feedforward Networks Yongjin Park 1 Goal of Feedforward Networks Deep Feedforward Networks are also called as Feedforward neural networks or Multilayer Perceptrons Their Goal: approximate some function

More information

". :'=: "t',.4 :; :::-':7'- --,r. "c:"" --; : I :. \ 1 :;,'I ~,:-._._'.:.:1... ~~ \..,i ... ~.. ~--~ ( L ;...3L-. ' f.':... I. -.1;':'.

. :'=: t',.4 :; :::-':7'- --,r. c: --; : I :. \ 1 :;,'I ~,:-._._'.:.:1... ~~ \..,i ... ~.. ~--~ ( L ;...3L-. ' f.':... I. -.1;':'. = 47 \ \ L 3L f \ / \ L \ \ j \ \ 6! \ j \ / w j / \ \ 4 / N L5 Dm94 O6zq 9 qmn j!!! j 3DLLE N f 3LLE Of ADL!N RALROAD ORAL OR AL AOAON N 5 5 D D 9 94 4 E ROL 2LL RLLAY RL AY 3 ER OLLL 832 876 8 76 L A

More information

Deep Learning (CNNs)

Deep Learning (CNNs) 10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Deep Learning (CNNs) Deep Learning Readings: Murphy 28 Bishop - - HTF - - Mitchell

More information

Interpreting Deep Classifiers

Interpreting Deep Classifiers Ruprecht-Karls-University Heidelberg Faculty of Mathematics and Computer Science Seminar: Explainable Machine Learning Interpreting Deep Classifiers by Visual Distillation of Dark Knowledge Author: Daniela

More information

Deep Feedforward Networks. Sargur N. Srihari

Deep Feedforward Networks. Sargur N. Srihari Deep Feedforward Networks Sargur N. srihari@cedar.buffalo.edu 1 Topics Overview 1. Example: Learning XOR 2. Gradient-Based Learning 3. Hidden Units 4. Architecture Design 5. Backpropagation and Other Differentiation

More information

The connection of dropout and Bayesian statistics

The connection of dropout and Bayesian statistics The connection of dropout and Bayesian statistics Interpretation of dropout as approximate Bayesian modelling of NN http://mlg.eng.cam.ac.uk/yarin/thesis/thesis.pdf Dropout Geoffrey Hinton Google, University

More information

arxiv: v4 [quant-ph] 13 Mar 2013

arxiv: v4 [quant-ph] 13 Mar 2013 Deep learning and the renormalization group arxiv:1301.3124v4 [quant-ph] 13 Mar 2013 Cédric Bény Institut für Theoretische Physik Leibniz Universität Hannover Appelstraße 2, 30167 Hannover, Germany cedric.beny@gmail.com

More information

Journal Club: Brief Introduction to Tensor Network

Journal Club: Brief Introduction to Tensor Network Journal Club: Brief Introduction to Tensor Network Wei-Han Hsiao a a The University of Chicago E-mail: weihanhsiao@uchicago.edu Abstract: This note summarizes the talk given on March 8th 2016 which was

More information

What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1

What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1 What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1 Multi-layer networks Steve Renals Machine Learning Practical MLP Lecture 3 7 October 2015 MLP Lecture 3 Multi-layer networks 2 What Do Single

More information

4 Matrix product states

4 Matrix product states Physics 3b Lecture 5 Caltech, 05//7 4 Matrix product states Matrix product state (MPS) is a highly useful tool in the study of interacting quantum systems in one dimension, both analytically and numerically.

More information

Chapter 4 Rigid Models and Angular Momentum Eigenstates Homework Solutions

Chapter 4 Rigid Models and Angular Momentum Eigenstates Homework Solutions Capter 4 Rigid Models and Angular Momentum Eigenstates Homework Solutions 1. A i j k B i 4j k AB AB AB AB()() ( 1)(4) ()( ) 4 x x y y z z i j k i j k AxB A A A 1 x y z Bx By Bz 4 i j k 5i 1 j 14k ( 1)(

More information

Executive Committee and Officers ( )

Executive Committee and Officers ( ) Gifted and Talented International V o l u m e 2 4, N u m b e r 2, D e c e m b e r, 2 0 0 9. G i f t e d a n d T a l e n t e d I n t e r n a t i o n a2 l 4 ( 2), D e c e m b e r, 2 0 0 9. 1 T h e W o r

More information

The density matrix renormalization group and tensor network methods

The density matrix renormalization group and tensor network methods The density matrix renormalization group and tensor network methods Outline Steve White Exploiting the low entanglement of ground states Matrix product states and DMRG 1D 2D Tensor network states Some

More information

CS Machine Learning Qualifying Exam

CS Machine Learning Qualifying Exam CS Machine Learning Qualifying Exam Georgia Institute of Technology March 30, 2017 The exam is divided into four areas: Core, Statistical Methods and Models, Learning Theory, and Decision Processes. There

More information

Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box

Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton Motivation Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses

More information

Domain adaptation for deep learning

Domain adaptation for deep learning What you saw is not what you get Domain adaptation for deep learning Kate Saenko Successes of Deep Learning in AI A Learning Advance in Artificial Intelligence Rivals Human Abilities Deep Learning for

More information

Trade Patterns, Production networks, and Trade and employment in the Asia-US region

Trade Patterns, Production networks, and Trade and employment in the Asia-US region Trade Patterns, Production networks, and Trade and employment in the Asia-U region atoshi Inomata Institute of Developing Economies ETRO Development of cross-national production linkages, 1985-2005 1985

More information

SOUTHWESTERN ELECTRIC POWER COMPANY SCHEDULE H-6.1b NUCLEAR UNIT OUTAGE DATA. For the Test Year Ended March 31, 2009

SOUTHWESTERN ELECTRIC POWER COMPANY SCHEDULE H-6.1b NUCLEAR UNIT OUTAGE DATA. For the Test Year Ended March 31, 2009 Schedule H-6.lb SOUTHWSTRN LCTRIC POWR COMPANY SCHDUL H-6.1b NUCLAR UNIT OUTAG DATA For the Test Year nded March 31, 29 This schedule is not applicable to SVvPCO. 5 Schedule H-6.1 c SOUTHWSTRN LCTRIC POWR

More information

Renormalization of Tensor Network States

Renormalization of Tensor Network States Renormalization of Tensor Network States I. Coarse Graining Tensor Renormalization Tao Xiang Institute of Physics Chinese Academy of Sciences txiang@iphy.ac.cn Numerical Renormalization Group brief introduction

More information

Quantum simulation with string-bond states: Joining PEPS and Monte Carlo

Quantum simulation with string-bond states: Joining PEPS and Monte Carlo Quantum simulation with string-bond states: Joining PEPS and Monte Carlo N. Schuch 1, A. Sfondrini 1,2, F. Mezzacapo 1, J. Cerrillo 1,3, M. Wolf 1,4, F. Verstraete 5, I. Cirac 1 1 Max-Planck-Institute

More information

PCA & ICA. CE-717: Machine Learning Sharif University of Technology Spring Soleymani

PCA & ICA. CE-717: Machine Learning Sharif University of Technology Spring Soleymani PCA & ICA CE-717: Machine Learning Sharif University of Technology Spring 2015 Soleymani Dimensionality Reduction: Feature Selection vs. Feature Extraction Feature selection Select a subset of a given

More information

Machine Learning (CS 567) Lecture 2

Machine Learning (CS 567) Lecture 2 Machine Learning (CS 567) Lecture 2 Time: T-Th 5:00pm - 6:20pm Location: GFS118 Instructor: Sofus A. Macskassy (macskass@usc.edu) Office: SAL 216 Office hours: by appointment Teaching assistant: Cheol

More information

ARestricted Boltzmann machine (RBM) [1] is a probabilistic

ARestricted Boltzmann machine (RBM) [1] is a probabilistic 1 Matrix Product Operator Restricted Boltzmann Machines Cong Chen, Kim Batselier, Ching-Yun Ko, and Ngai Wong chencong@eee.hku.hk, k.batselier@tudelft.nl, cyko@eee.hku.hk, nwong@eee.hku.hk arxiv:1811.04608v1

More information

Experiments on the Consciousness Prior

Experiments on the Consciousness Prior Yoshua Bengio and William Fedus UNIVERSITÉ DE MONTRÉAL, MILA Abstract Experiments are proposed to explore a novel prior for representation learning, which can be combined with other priors in order to

More information

Course Structure. Psychology 452 Week 12: Deep Learning. Chapter 8 Discussion. Part I: Deep Learning: What and Why? Rufus. Rufus Processed By Fetch

Course Structure. Psychology 452 Week 12: Deep Learning. Chapter 8 Discussion. Part I: Deep Learning: What and Why? Rufus. Rufus Processed By Fetch Psychology 452 Week 12: Deep Learning What Is Deep Learning? Preliminary Ideas (that we already know!) The Restricted Boltzmann Machine (RBM) Many Layers of RBMs Pros and Cons of Deep Learning Course Structure

More information

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net Supplementary Material Xingang Pan 1, Ping Luo 1, Jianping Shi 2, and Xiaoou Tang 1 1 CUHK-SenseTime Joint Lab, The Chinese University

More information

Grundlagen der Künstlichen Intelligenz

Grundlagen der Künstlichen Intelligenz Grundlagen der Künstlichen Intelligenz Neural networks Daniel Hennes 21.01.2018 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Logistic regression Neural networks Perceptron

More information

Unsupervised Learning of Hierarchical Models. in collaboration with Josh Susskind and Vlad Mnih

Unsupervised Learning of Hierarchical Models. in collaboration with Josh Susskind and Vlad Mnih Unsupervised Learning of Hierarchical Models Marc'Aurelio Ranzato Geoff Hinton in collaboration with Josh Susskind and Vlad Mnih Advanced Machine Learning, 9 March 2011 Example: facial expression recognition

More information

Learning to Disentangle Factors of Variation with Manifold Learning

Learning to Disentangle Factors of Variation with Manifold Learning Learning to Disentangle Factors of Variation with Manifold Learning Scott Reed Kihyuk Sohn Yuting Zhang Honglak Lee University of Michigan, Department of Electrical Engineering and Computer Science 08

More information

Quantum many-body systems and tensor networks: simulation methods and applications

Quantum many-body systems and tensor networks: simulation methods and applications Quantum many-body systems and tensor networks: simulation methods and applications Román Orús School of Physical Sciences, University of Queensland, Brisbane (Australia) Department of Physics and Astronomy,

More information

Generative Adversarial Networks

Generative Adversarial Networks Generative Adversarial Networks SIBGRAPI 2017 Tutorial Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask Presentation content inspired by Ian Goodfellow s tutorial

More information

How to do backpropagation in a brain

How to do backpropagation in a brain How to do backpropagation in a brain Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto & Google Inc. Prelude I will start with three slides explaining a popular type of deep

More information

Guiding Monte Carlo Simulations with Machine Learning

Guiding Monte Carlo Simulations with Machine Learning Guiding Monte Carlo Simulations with Machine Learning Yang Qi Department of Physics, Massachusetts Institute of Technology Joining Fudan University in 2017 KITS, June 29 2017. 1/ 33 References Works led

More information

Why is Deep Learning so effective?

Why is Deep Learning so effective? Ma191b Winter 2017 Geometry of Neuroscience The unreasonable effectiveness of deep learning This lecture is based entirely on the paper: Reference: Henry W. Lin and Max Tegmark, Why does deep and cheap

More information

We choose parameter values that will minimize the difference between the model outputs & the true function values.

We choose parameter values that will minimize the difference between the model outputs & the true function values. CSE 4502/5717 Big Data Analytics Lecture #16, 4/2/2018 with Dr Sanguthevar Rajasekaran Notes from Yenhsiang Lai Machine learning is the task of inferring a function, eg, f : R " R This inference has to

More information

A Gentle Introduction to Gradient Boosting. Cheng Li College of Computer and Information Science Northeastern University

A Gentle Introduction to Gradient Boosting. Cheng Li College of Computer and Information Science Northeastern University A Gentle Introduction to Gradient Boosting Cheng Li chengli@ccs.neu.edu College of Computer and Information Science Northeastern University Gradient Boosting a powerful machine learning algorithm it can

More information

The Origin of Deep Learning. Lili Mou Jan, 2015

The Origin of Deep Learning. Lili Mou Jan, 2015 The Origin of Deep Learning Lili Mou Jan, 2015 Acknowledgment Most of the materials come from G. E. Hinton s online course. Outline Introduction Preliminary Boltzmann Machines and RBMs Deep Belief Nets

More information

CS 6375 Machine Learning

CS 6375 Machine Learning CS 6375 Machine Learning Nicholas Ruozzi University of Texas at Dallas Slides adapted from David Sontag and Vibhav Gogate Course Info. Instructor: Nicholas Ruozzi Office: ECSS 3.409 Office hours: Tues.

More information

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)

More information

Large-Scale Feature Learning with Spike-and-Slab Sparse Coding

Large-Scale Feature Learning with Spike-and-Slab Sparse Coding Large-Scale Feature Learning with Spike-and-Slab Sparse Coding Ian J. Goodfellow, Aaron Courville, Yoshua Bengio ICML 2012 Presented by Xin Yuan January 17, 2013 1 Outline Contributions Spike-and-Slab

More information

Neural Networks. William Cohen [pilfered from: Ziv; Geoff Hinton; Yoshua Bengio; Yann LeCun; Hongkak Lee - NIPs 2010 tutorial ]

Neural Networks. William Cohen [pilfered from: Ziv; Geoff Hinton; Yoshua Bengio; Yann LeCun; Hongkak Lee - NIPs 2010 tutorial ] Neural Networks William Cohen 10-601 [pilfered from: Ziv; Geoff Hinton; Yoshua Bengio; Yann LeCun; Hongkak Lee - NIPs 2010 tutorial ] WHAT ARE NEURAL NETWORKS? William s notation Logis;c regression + 1

More information

Deep Generative Models. (Unsupervised Learning)

Deep Generative Models. (Unsupervised Learning) Deep Generative Models (Unsupervised Learning) CEng 783 Deep Learning Fall 2017 Emre Akbaş Reminders Next week: project progress demos in class Describe your problem/goal What you have done so far What

More information

2014 CANADIAN SURF LIFESAVING CHAMPIONSHIPS PROGRAM

2014 CANADIAN SURF LIFESAVING CHAMPIONSHIPS PROGRAM 2014 CANAIAN URF LIFEAVING CHAMPIONHIP PROGRAM Lv Lv vy b v, w,, w Lv y w k Lv z by I Oy C (IOC) Cw G F T IOC z I L v F (IL) w v v IL N Mb Oz v b v T Lv y v by v C I Lv W C z I L v F Cw Lv C z Ry L v y

More information

Image classification via Scattering Transform

Image classification via Scattering Transform 1 Image classification via Scattering Transform Edouard Oyallon under the supervision of Stéphane Mallat following the work of Laurent Sifre, Joan Bruna, Classification of signals Let n>0, (X, Y ) 2 R

More information

Deep learning on 3D geometries. Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering

Deep learning on 3D geometries. Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering Deep learning on 3D geometries Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering Overview Background Methods Numerical Result Future improvements Conclusion Background

More information

E.., (2) g t = e 2' g E. g t = g ij (t u k )du i du j, i j k =1 2. (u 1 0 0) u2 2 U, - v, w, g 0 (v w) = g ij (0 u k 0)v i w j = 0, (t) = g ij (t u k

E.., (2) g t = e 2' g E. g t = g ij (t u k )du i du j, i j k =1 2. (u 1 0 0) u2 2 U, - v, w, g 0 (v w) = g ij (0 u k 0)v i w j = 0, (t) = g ij (t u k 2007 10 (545) 517.929..,.. 1. g t M, d dt g t = ;2 Ric(g t ) (1) Ric(g) g.,, -, - (., [1], [2]).,,.,, f t - (M G), g t = ft G,, (1)., -, -, (, ), - (,, [3]). t - E 3, g t, t E 3, (1). t -., -. (M g) Ric

More information

Statistical Pattern Recognition

Statistical Pattern Recognition Statistical Pattern Recognition Feature Extraction Hamid R. Rabiee Jafar Muhammadi, Alireza Ghasemi, Payam Siyari Spring 2014 http://ce.sharif.edu/courses/92-93/2/ce725-2/ Agenda Dimensionality Reduction

More information

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /9/17

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /9/17 3/9/7 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/9/7 Perceptron as a neural

More information

!"# $ % & '( INRA-RP-RE /71-0-Tir.1395

!# $ % & '( INRA-RP-RE /71-0-Tir.1395 !"# $ ) ) 1395 /-. ٠ 4 21645 ) 89 ;$ 4 ) < 1...>? 1... 1...A 3... D, /9C 3...D 6E 5... 7... )KH6/J /9CHA!HG? 13...)K M & H?# 14...O 16...& 16... 17... 54 18...& NH -1-2 -3-4 -5-6 -7-8 -9-10 54Q/ -11 R#

More information

f;g,7k ;! / C+!< 8R+^1 ;0$ Z\ \ K S;4 i!;g + 5 ;* \ C! 1+M, /A+1+> 0 /A+>! 8 J 4! 9,7 )F C!.4 ;* )F /0 u+\ 30< #4 8 J C!

f;g,7k ;! / C+!< 8R+^1 ;0$ Z\ \ K S;4 i!;g + 5 ;* \ C! 1+M, /A+1+> 0 /A+>! 8 J 4! 9,7 )F C!.4 ;* )F /0 u+\ 30< #4 8 J C! 393/09/0 393//07 :,F! ::!n> b]( a.q 5 O +D5 S ١ ; ;* :'!3Qi C+0;$ < "P 4 ; M V! M V! ; a 4 / ;0$ f;g,7k ;! / C+!< 8R+^ ;0$ Z\ \ K S;4 "* < 8c0 5 *

More information

I M P O R T A N T S A F E T Y I N S T R U C T I O N S W h e n u s i n g t h i s e l e c t r o n i c d e v i c e, b a s i c p r e c a u t i o n s s h o

I M P O R T A N T S A F E T Y I N S T R U C T I O N S W h e n u s i n g t h i s e l e c t r o n i c d e v i c e, b a s i c p r e c a u t i o n s s h o I M P O R T A N T S A F E T Y I N S T R U C T I O N S W h e n u s i n g t h i s e l e c t r o n i c d e v i c e, b a s i c p r e c a u t i o n s s h o u l d a l w a y s b e t a k e n, i n c l u d f o l

More information

ECE Lecture 1. Terminology. Statistics are used much like a drunk uses a lamppost: for support, not illumination

ECE Lecture 1. Terminology. Statistics are used much like a drunk uses a lamppost: for support, not illumination ECE471-571 Lecture 1 Introduction Statistics are used much like a drunk uses a lamppost: for support, not illumination -- Vin Scully ECE471/571, Hairong Qi 2 Terminology Feature Sample Dimension Pattern

More information

PHYS 232 QUIZ minutes.

PHYS 232 QUIZ minutes. / PHYS 232 QUIZ 1 02-18-2005 50 minutes. This quiz has 3 questions. Please show all your work. If your final answer is not correct, you will get partial credit based on your work shown. You are allowed

More information

N e w S t u d e n t. C o u n c i l M e n

N e w S t u d e n t. C o u n c i l M e n ZV. XX L GG L 3 942. 25 J b D b v D G... j z U 6 b Y DY. j b D.. L......&. v b v. z " 6 D". " v b b bv D v.... v z b.. k."... 92... G b 92. b v v b v b D ( 6) z v 27 b b v " z". v b L G. b. v.. v v. D

More information

Exhibit 2-9/30/15 Invoice Filing Page 1841 of Page 3660 Docket No

Exhibit 2-9/30/15 Invoice Filing Page 1841 of Page 3660 Docket No xhibit 2-9/3/15 Invie Filing Pge 1841 f Pge 366 Dket. 44498 F u v 7? u ' 1 L ffi s xs L. s 91 S'.e q ; t w W yn S. s t = p '1 F? 5! 4 ` p V -', {} f6 3 j v > ; gl. li -. " F LL tfi = g us J 3 y 4 @" V)

More information

Machine Learning Basics

Machine Learning Basics Security and Fairness of Deep Learning Machine Learning Basics Anupam Datta CMU Spring 2019 Image Classification Image Classification Image classification pipeline Input: A training set of N images, each

More information

Principles of Pattern Recognition. C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata

Principles of Pattern Recognition. C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata Principles of Pattern Recognition C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata e-mail: murthy@isical.ac.in Pattern Recognition Measurement Space > Feature Space >Decision

More information

arxiv: v1 [cond-mat.str-el] 19 Jan 2012

arxiv: v1 [cond-mat.str-el] 19 Jan 2012 Perfect Sampling with Unitary Tensor Networks arxiv:1201.3974v1 [cond-mat.str-el] 19 Jan 2012 Andrew J. Ferris 1, 2 and Guifre Vidal 1, 3 1 The University of Queensland, School of Mathematics and Physics,

More information

Natural Language Processing with Deep Learning CS224N/Ling284

Natural Language Processing with Deep Learning CS224N/Ling284 Natural Language Processing with Deep Learning CS224N/Ling284 Lecture 4: Word Window Classification and Neural Networks Richard Socher Organization Main midterm: Feb 13 Alternative midterm: Friday Feb

More information

Machine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function.

Machine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function. Bayesian learning: Machine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function. Let y be the true label and y be the predicted

More information

Tensor networks and deep learning

Tensor networks and deep learning Tensor networks and deep learning I. Oseledets, A. Cichocki Skoltech, Moscow 26 July 2017 What is a tensor Tensor is d-dimensional array: A(i 1,, i d ) Why tensors Many objects in machine learning can

More information

Improved Bayesian Compression

Improved Bayesian Compression Improved Bayesian Compression Marco Federici University of Amsterdam marco.federici@student.uva.nl Karen Ullrich University of Amsterdam karen.ullrich@uva.nl Max Welling University of Amsterdam Canadian

More information

h : sh +i F J a n W i m +i F D eh, 1 ; 5 i A cl m i n i sh» si N «q a : 1? ek ser P t r \. e a & im a n alaa p ( M Scanned by CamScanner

h : sh +i F J a n W i m +i F D eh, 1 ; 5 i A cl m i n i sh» si N «q a : 1? ek ser P t r \. e a & im a n alaa p ( M Scanned by CamScanner m m i s t r * j i ega>x I Bi 5 n ì r s w «s m I L nk r n A F o n n l 5 o 5 i n l D eh 1 ; 5 i A cl m i n i sh» si N «q a : 1? { D v i H R o s c q \ l o o m ( t 9 8 6) im a n alaa p ( M n h k Em l A ma

More information

TUTORIAL PART 1 Unsupervised Learning

TUTORIAL PART 1 Unsupervised Learning TUTORIAL PART 1 Unsupervised Learning Marc'Aurelio Ranzato Department of Computer Science Univ. of Toronto ranzato@cs.toronto.edu Co-organizers: Honglak Lee, Yoshua Bengio, Geoff Hinton, Yann LeCun, Andrew

More information

STA 414/2104: Lecture 8

STA 414/2104: Lecture 8 STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks Delivered by Mark Ebden With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable

More information

Chair Susan Pilkington called the meeting to order.

Chair Susan Pilkington called the meeting to order. PGE PRK D RECREO DVOR COMMEE REGUR MEEG MUE MOD, JU, Ru M h P P d R d Cmm hd : m Ju,, h Cu Chmb C H P, z Ch u P dd, Mmb B C, Gm Cu D W Bd mmb b: m D, d Md z ud mmb : C M, J C P Cmmu Dm D, Km Jh Pub W M,

More information

An introduction to tensornetwork

An introduction to tensornetwork An introduction to tensornetwork states and MERA Sissa Journal Club Andrea De Luca 29/01/2010 A typical problem We are given: A lattice with N sites On each site a C d hilbert space A quantum hamiltonian

More information

Bayesian Learning. Two Roles for Bayesian Methods. Bayes Theorem. Choosing Hypotheses

Bayesian Learning. Two Roles for Bayesian Methods. Bayes Theorem. Choosing Hypotheses Bayesian Learning Two Roles for Bayesian Methods Probabilistic approach to inference. Quantities of interest are governed by prob. dist. and optimal decisions can be made by reasoning about these prob.

More information

Bayes Classifiers. CAP5610 Machine Learning Instructor: Guo-Jun QI

Bayes Classifiers. CAP5610 Machine Learning Instructor: Guo-Jun QI Bayes Classifiers CAP5610 Machine Learning Instructor: Guo-Jun QI Recap: Joint distributions Joint distribution over Input vector X = (X 1, X 2 ) X 1 =B or B (drinking beer or not) X 2 = H or H (headache

More information

7.2. Matrix Multiplication. Introduction. Prerequisites. Learning Outcomes

7.2. Matrix Multiplication. Introduction. Prerequisites. Learning Outcomes Matrix Multiplication 7.2 Introduction When we wish to multiply matrices together we have to ensure that the operation is possible - and this is not always so. Also, unlike number arithmetic and algebra,

More information

Fermionic tensor networks

Fermionic tensor networks Fermionic tensor networks Philippe Corboz, ETH Zurich / EPF Lausanne, Switzerland Collaborators: University of Queensland: Guifre Vidal, Roman Orus, Glen Evenbly, Jacob Jordan University of Vienna: Frank

More information