UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$18:$Neural'Network'/'Deep' Learning$

Size: px
Start display at page:

Download "UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$18:$Neural'Network'/'Deep' Learning$"

Transcription

1 UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$18:$NeuralNetwork/Deep Learning$ Dr.YanjunQi UniversityofVirginia Departmentof ComputerScience 1 Wherearewe?! FivemajorsecKonsofthiscourse " Regression(supervised) " ClassificaKon(supervised) " Unsupervisedmodels " Learningtheory " Graphicalmodels 2

2 A study comparing Classifiers Proceedingsofthe23rdInternaKonal ConferenceonMachineLearning(ICML`06). 3 A study comparing Classifiers! 11binaryclassificaKonproblems/8metrics Proceedingsofthe23rdInternaKonal ConferenceonMachineLearning(ICML`06). 4

3 A study comparing Classifiers! 11binaryclassificaKonproblems Proceedingsofthe23rdInternaKonal ConferenceonMachineLearning(ICML`06). 5 Today$ # BasicNeuralNetwork(NN) # singleneuron,e.g.logiskcregressionunit # mulklayerperceptron(mlp) # formulk\classclassificakon,so]maxlayer # MoreabouttrainingNN # DeepCNN,Deeplearning # History # Whyisthisbreakthrough? # RecentapplicaKons 6

4 Today$ # BasicNeuralNetwork(NN) # singleneuron,e.g.logiskcregressionunit # mulklayerperceptron(mlp) # formulk\classclassificakon,so]maxlayer # MoreabouttrainingNN # DeepCNN,Deeplearning # History # Whyisthisbreakthrough? # RecentapplicaKons 7 Logistic Regression Task classification Representation Score Function Log-odds(Y) = linear function of X s EPE, with conditional Log-likelihood Search/Optimization Iterative (Newton) method Models, Parameters Logistic weights 1 P( y = 1 x) = (α +βx) 1+ e 8

5 UsingLogisKcFuncKontoTransfer e.g. Probabilityof disease P (Y=1 X) α+ βx e P(y x) = α+ βx 1+ e x Logistic regression Logistic regression could be illustrated as a module On input x, it outputs ŷ: where Draw a logistic regression unit as: x 1 x 2 x 3 +1 Bias w T! x + b 1 1+ e z Σ Summing function Activation function Output ŷ=p(y=1 X,Θ) 10

6 1neuron,e.g. 1Neronexample x 1 w 1 x 2 w 2 w 3 Σ Output x 3 +1 Bias b Summing function Activation function 11 Transfer / Activation functions Common ones include: Threshold / Step function: f(v) = 1 if v > c, else -1 Sigmoid (s shape func): E.g. logistic func: f(v) = 1/(1 + e -v ), Range [0, 1] Hyperbolic Tanh : f(v) = (e v e -v )/ (e v + e -v ), Range [-1,1] sigmoid func 1 a 0 0 z a = e z Desirable properties: Monotonic, Nonlinear, Bounded Easily calculated derivative step func 12

7 Perceptron:$Another$1ENeuron$Unit (Specialformofsinglelayerfeedforward) TheperceptronwasfirstproposedbyRosenblaj (1958)isasimpleneuronthatisusedtoclassify itsinputintooneoftwocategories. Aperceptronusesastep$funcIonthatreturns+1 ifweightedsumofitsinputlargeorequalto0, and\1otherwise b (bias) + 1if v 0 ϕ( v) = x 1 1if v < 0 x 2 x n w 1 w 2 w n Σ v Summing function φ(v) y Activation (Step) function 13 Today$ # BasicNeuralNetwork(NN) # singleneuron,e.g.logiskcregressionunit # mulklayerperceptron(mlp) # formulk\classclassificakon,so]maxlayer # MoreabouttrainingNN # DeepCNN,Deeplearning # History # Whyisthisbreakthrough? # RecentapplicaKons 14

8 SingleLayerFeed\forward i.e.(onelayerof4outputneurons) Input layer of source nodes Output layer of neurons! y!" input output Fourneurons 15 MulK\LayerPerceptron(MLP) String a lot of logistic units together. Example: 3 layer network: x 1 x 2 a 1 a 2 a 3 y x 3 Layer Layer1 Layer2 input hidden output 16

9 MulK\LayerPerceptron(MLP) Example:4layernetworkwith2outputunits: x 1 x 2 x 3! y!" Layer3 Layer4 Layer1 Layer2 input hidden hidden output 17 Types of Neural Networks (according to different attributes) Connection Type (e.g. - Static (feed-forward) - Dynamic (feedback) Topology (e.g. - Single layer - Multilayer - Recurrent - Recursive - Self-organized Learning Methods (e.g. - Supervised - Unsupervised 18

10 Youcangoverycrazywith designingsuchneuralnetworks.. Prof.NandodeFreitas slide 19 Today$ # BasicNeuralNetwork(NN) #singleneuron,e.g.logiskcregressionunit #mulklayerperceptron(mlp) #formulk\classclassificakon,so]maxlayer #MoreabouttrainingNN # DeepCNN,Deeplearning #History #Whyisthisbreakthrough? #RecentapplicaKons 20

11 WhenforRegression j k w jk (y k -ŷ k ) TrainingNNin orderto minimizethe networktotal sumsquared error(sse). v ij i 21 WhenforclassificaKon (e.g.1neuronforbinaryoutputlayer) ŷ=p(y=1 X,Θ) j ForBernoullidistribuKon, p(y =1 x) y (1 p) 1 y i N E(θ) = Loss(θ) = {logpr(y = y i X = x i )} N i=1 = y i log(ŷ i )+ (1 y i )log(1 ŷ i ) i=1 Cross\entropylossfuncKon,ORnamedas deviance 22

12 y 1 z y y 2 3 z 1 2 z Outputunits 3 WhenformulK\classclassificaKon (lastoutputlayer:so]maxlayer) WhenmulK\classoutput,lastlayeris so]maxoutputlayer!a mulknomiallogiskcregressionunit 23 Review:$$$MulIE class$variable$ representaion$$ Class MulK\classvariable! Anindicatorbasisvector representakon IfoutputvariableGhasK classes,therewillbekindicator variabley_i N f 1 (x),f 2 (x),f 3 (x),f 4 (x) HowtoclassifytomulK\class? StrategyI:learnKdifferent regressionfunckons,thenmax 24

13 StrategyII:Use so]max layerfunckonfor mulk\classclassificakon y 1 y y 2 3 So]max Output z z 1 2 z 3 y i = j ez i e z j y i z i = y i (1 y i ) 25 Use so]max layerfunckonfor mulk\classclassificakon ThenaturalcostfuncKonisthe negakvelogproboftherightanswer!crossentropylossfunckon: E x () = E z i = j truey j ln y j = truey j ln p(y j =1 x) j=1...k E y j = y i truey i y j z i j Errorcalculated fromoutputvs. true ThesteepnessoffuncKonEexactlybalancesthe flatnessoftheso]max 26

14 Aspecialcaseofso]maxfortwoclasses y 1 = e z 1 e z 1 + e z 0 = 1+ e 1 ( z 1 z 0 ) SothelogisKcisjustaspecialcasethatavoids usingredundantparameters: Addingthesameconstanttobothz1andz0has noeffect. Theover\parameterizaKonoftheso]maxis becausetheprobabilikesmustaddto1. 27 Today$ # BasicNeuralNetwork(NN) # singleneuron,e.g.logiskcregressionunit # mulklayerperceptron(mlp) # formulk\classclassificakon,so]maxlayer # MoreabouttrainingMLPNN # DeepCNN,Deeplearning # History # Whyisthisbreakthrough? # RecentapplicaKons 28

15 Backpropagation Using backward recurrence to jointly optimize all parameters Requires all activation functions to be differentiable Enables flexible design in deep model architecture Gradient descent is used to (locally) minimize objective: W k+1 = W k η E W k Y. LeCun et al Efficient BackProp. Olivier Bousquet and Ulrike von Luxburg Stochastic Learning. 29 Training a neural network Given training set (x 1, y 1 ), (x 2, y 2 ), (x 3, y 3 ),. Adjust parameters (for every node) to make: the predicted output close to true label (Use gradient descent. Backpropagation algorithm. Susceptible to local optima.) 30

16 Review:LinearRegressionwith StochasKcGD! Wehavethefollowingdescentrule: n 1 T J ( θ ) = ( xi θ yi ) 2 i= 1 2 t+1 t θ j = θ j α J (θ ) θ Howdowepickα? 1. Tuning set, or 2. Cross validation, or 3. Small for slow, conservative learning j t 31 ForLR:linearregression,Wehavethe followingdescentrule: Review:StochasKcGD! t+1 t θ j = θ j α J (θ ) θ!forneuralnetwork,wehavethedeltarule j t Δw = η E W t W t+1 = W t η E! W = W t + Δw t 32

17 Backpropagation Back\propagaKontrainingalgorithm Network activation Forward Step Error propagation Backward Step 33 Forinstance!forregression for sigmoid unit o, its derivative is, o (h) = o(h) * (1 - o(h)) input x 1 x 2 +1 w 1 w 2 w 3 w 4 b 1 b 2 Output h 1 Σ Σ Θ 1 Output o 1 w 6 h 2 o 2 w 5 Σ f 1 f 2 f 3 +1 b 3 Output ŷ f 4 Θ 1 Θ 2 Θ 3 Θ 4 E(y,ŷ) T=4 34

18 35 Dr.QI scikm2012paper/talk 36

19 37 T Error propagation Backward Step Dr.QI scikm2012paper/talk 38

20 Backpropagation 1.IniKalizenetworkwithrandomweights 2.Foralltrainingcases(examples): a.presenttraininginputstonetworkand calculateoutputofeachlayer,andfinallayer b.foralllayers(starkngwiththeoutput layer,backtoinputlayer): i.comparenetworkoutputwithcorrectoutput (errorfunckon) ii.adaptweightsincurrentlayer W t+1 = W t η E W t 39 Backpropagation Algorithm Main Idea: error in hidden layers The ideas of the algorithm can be summarized as follows : 1. Computes the error term for the output units using the observed error. 2. From output layer, repeat - propagating the error term back to the previous layer and - updating the weights between the two layers until the earliest hidden layer is reached. 40

21 Today$ # BasicNeuralNetwork(NN) # singleneuron,e.g.logiskcregressionunit # mulklayerperceptron(mlp) # formulk\classclassificakon,so]maxlayer # MoreabouttrainingNN # DeepCNN,Deeplearning # History # Whyisthisbreakthrough? # RecentapplicaKons 41 ManyclassificaKonmodels inventedsincelate80 s Neuralnetworks BoosKng SupportVectorMachine MaximumEntropy RandomForest 42

22 DeepLearninginthe90 s Prof.YannLeCuninventedConvoluKonal NeuralNetworks FirstNNsuccessfullytrainedwithmanylayers 43 LetNet EarlysuccessatOCR Y.LeCun,L.Bojou,Y.Bengio,andP.Haffner,Gradient\basedlearningappliedtodocumentrecogniKon, ProceedingsoftheIEEE86(11): ,

23 Between~2000to~2011 MachineLearningFieldInterest LearningwithStructures! Kernellearning TransferLearning Semi\supervised ManifoldLearning SparseLearning Structuredinput\outputlearning Graphicalmodel 45 Winter$of$Neural$Networks $ Since$90 s$!$$$$$to~2010 Non\convex Needalotoftrickstoplaywith Howmanylayers? Howmanyhiddenunitsperlayer? Whattopologyamonglayers?. HardtoperformtheoreKcalanalysis 46

24 Today$ # BasicNeuralNetwork(NN) # singleneuron,e.g.logiskcregressionunit # mulklayerperceptron(mlp) # formulk\classclassificakon,so]maxlayer # MoreabouttrainingNN # DeepCNN,Deeplearning # History # Whyisthisabreakthrough? # RecentapplicaKons 47 Large\ScaleVisualRecogniKonChallenge % 30% Errorrate 25% 20% 15% 10% 10%improve withdeepcnn 5% 0% ISI OXFORD_VGG XRCE/INRIA Universityof Amsterdam LEAR\XRCE SuperVision 48

25 SpeechRecogniKon Year % 50.0% Worderrorrate 25.0% HMM\GMM Hasn tbeabletoimprove for10years!!! 12.5% 6.3% 49 Read ConversaKonal Source:Huangetal.,CommunicaKonsACM01/

26 WHY$BREAKTHROUGH$?$$ 51 Howcanwebuildmoreintelligent computer/machine? Ableto perceive$the$world$ understand$the$world$$ Thisneeds BasicspeechcapabiliKes BasicvisioncapabiliKes Languageunderstanding Userbehavior/emoKonunderstanding Abletothink?? 52

27 PlentyofData Text:trillionsofwordsofEnglish+otherlanguages Visual:billionsofimagesandvideos Audio:thousandsofhoursofspeechperday UseracKvity:queries,userpageclicks,maprequests,etc, Knowledgegraph:billionsoflabeledrelaKonaltriplets Dr.JeffDean stalk 53 Deep$Learning$Way:$$ Learning$features$/$RepresentaIon$from$data Feature Engineering $ Most critical for accuracy $ # Account for most of the computation for testing $ #Most time-consuming in development cycle $ # Often hand-craft and task dependent in practice Feature Learning $ Easily adaptable to new similar tasks $ Layerwise representation $ Layer-by-layer unsupervised training $ Layer-by-layer supervised training 54

28 DESIGN ISSUES for Deep$NN DatarepresentaKon NetworkTopology NetworkParameters Training Scaling up with graphics processors Scaling up with Asynchronous$SGD ValidaKon 55 Today$ # BasicNeuralNetwork(NN) # singleneuron,e.g.logiskcregressionunit # mulklayerperceptron(mlp) # formulk\classclassificakon,so]maxlayer # MoreabouttrainingNN # DeepCNN,Deeplearning # History # Whyisthisabreakthrough? # RecentapplicaKons 56

29 Application I: Objective Recognition / Image Labeling Deep Convolution Neural Network (CNN) won (as Best systems) on very large-scale ImageNet competition 2012 / 2013 / 2014 (training on 1.2 million images [X] vs.1000 different word labels [Y]) 89%, 2013 \2013,GoogleAcquiredDeepNeuralNetworksCompanyheadedby Utoronto DeepLearning ProfessorHinton \2013,FacebookBuiltNewArKficialIntelligenceLabheadedbyNYU DeepLearning ProfessorLeCun 57 OlivierGrisel stalk 58

30 Dr.JeffDean stalk 59 OlivierGrisel stalk Application II: Semantic Understanding Wordembedding(e.g.googleword2vector/skipgram) Learn to embed each word into a vector of real values Semantically similar words have closer embedding representations Progress in 2013/14 CanuncoversemanKc/syntacKcwordrelaKonships Dr.LiDeng stalk Dr.JeffDean stalk 60

31 61 Application III: Deep LearningtoPlayGame DeepMind:LearningtoPlay&windozensof Atarigames anewdeepreinforcementlearningalgorithm OlivierGrisel stalk 62

32 Application IV: DeepLearningto ExecuteandProgram GoogleBrain&NYU,October2014 RNNtrainedtomapcharacterrepresentaKons ofprogramstooutputs CanlearntoemulateasimplisKcPython interpreterlimitedtoone\passprogramswith O(n)complexity OlivierGrisel stalk 63 Application IV: DeepLearningto ExecuteandProgram OlivierGrisel stalk 64

33 Summary$$ # BasicNeuralNetwork(NN) # singleneuron,e.g.logiskcregressionunit # mulklayerperceptron(mlp) # formulk\classclassificakon,so]maxlayer # MoreabouttrainingNN # DeepCNN,Deeplearning # History # Whyisthisabreakthrough? # RecentapplicaKons 65 References$$ " Dr.YannLecun sdeeplearningtutorials " Dr.LiDeng sicml2014deeplearningtutorial " Dr.KaiYu sdeeplearningtutorial " Dr.RobFergus deeplearningtutorial " Prof.NandodeFreitas slides " OlivierGrisel stalkatparisdatageeks/open WorldForum " HasKe,Trevor,etal.Theelementsofsta7s7cal learning.vol.2.no.1.newyork:springer,

Announcements:!Rough!Plan!!

Announcements:!Rough!Plan!! UVA$CS$4501$+$001$/$6501$ $007$ Introduc8on$to$Machine$Learning$and$ Data$Mining$$ $ Lecture$26:History/Review$ YanjunQi/Jane,,PhD UniversityofVirginia Departmentof ComputerScience YanjunQi/UVACS4501O01O6501O07

More information

Lecture 17: Neural Networks and Deep Learning

Lecture 17: Neural Networks and Deep Learning UVA CS 6316 / CS 4501-004 Machine Learning Fall 2016 Lecture 17: Neural Networks and Deep Learning Jack Lanchantin Dr. Yanjun Qi 1 Neurons 1-Layer Neural Network Multi-layer Neural Network Loss Functions

More information

CSE446: Neural Networks Spring Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer

CSE446: Neural Networks Spring Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer CSE446: Neural Networks Spring 2017 Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer Human Neurons Switching time ~ 0.001 second Number of neurons 10 10 Connections per neuron 10 4-5 Scene

More information

Intro to Neural Networks and Deep Learning

Intro to Neural Networks and Deep Learning Intro to Neural Networks and Deep Learning Jack Lanchantin Dr. Yanjun Qi UVA CS 6316 1 Neurons 1-Layer Neural Network Multi-layer Neural Network Loss Functions Backpropagation Nonlinearity Functions NNs

More information

ECE521 Lectures 9 Fully Connected Neural Networks

ECE521 Lectures 9 Fully Connected Neural Networks ECE521 Lectures 9 Fully Connected Neural Networks Outline Multi-class classification Learning multi-layer neural networks 2 Measuring distance in probability space We learnt that the squared L2 distance

More information

Neural Networks. Yan Shao Department of Linguistics and Philology, Uppsala University 7 December 2016

Neural Networks. Yan Shao Department of Linguistics and Philology, Uppsala University 7 December 2016 Neural Networks Yan Shao Department of Linguistics and Philology, Uppsala University 7 December 2016 Outline Part 1 Introduction Feedforward Neural Networks Stochastic Gradient Descent Computational Graph

More information

4. Multilayer Perceptrons

4. Multilayer Perceptrons 4. Multilayer Perceptrons This is a supervised error-correction learning algorithm. 1 4.1 Introduction A multilayer feedforward network consists of an input layer, one or more hidden layers, and an output

More information

Machine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6

Machine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6 Machine Learning for Large-Scale Data Analysis and Decision Making 80-629-17A Neural Networks Week #6 Today Neural Networks A. Modeling B. Fitting C. Deep neural networks Today s material is (adapted)

More information

UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$5:$NonALinear$Regression$ Models$

UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$5:$NonALinear$Regression$ Models$ UVACS6316 Fall15Graduate: MachineLearning Lecture5:NonALinearRegression Models 9/1/15 Dr.YanjunQi UniversityofVirginia Departmentof ComputerScience 1 Whereweare?! FivemajorsecHonsofthiscourse " Regression(supervised)

More information

UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$4:$More$opBmizaBon$for$Linear$ Regression$

UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$4:$More$opBmizaBon$for$Linear$ Regression$ Dr.YanjunQi/UVACS6316/f15 UVACS6316 Fall2015Graduate: MachineLearning Lecture4:MoreopBmizaBonforLinear Regression 9/14/15 Dr.YanjunQi UniversityofVirginia Departmentof ComputerScience 1 Whereweare?! FivemajorsecHonsofthiscourse

More information

Statistical NLP for the Web

Statistical NLP for the Web Statistical NLP for the Web Neural Networks, Deep Belief Networks Sameer Maskey Week 8, October 24, 2012 *some slides from Andrew Rosenberg Announcements Please ask HW2 related questions in courseworks

More information

Lecture 10. Neural networks and optimization. Machine Learning and Data Mining November Nando de Freitas UBC. Nonlinear Supervised Learning

Lecture 10. Neural networks and optimization. Machine Learning and Data Mining November Nando de Freitas UBC. Nonlinear Supervised Learning Lecture 0 Neural networks and optimization Machine Learning and Data Mining November 2009 UBC Gradient Searching for a good solution can be interpreted as looking for a minimum of some error (loss) function

More information

Artificial Intelligence

Artificial Intelligence Artificial Intelligence Jeff Clune Assistant Professor Evolving Artificial Intelligence Laboratory Announcements Be making progress on your projects! Three Types of Learning Unsupervised Supervised Reinforcement

More information

(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann

(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann (Feed-Forward) Neural Networks 2016-12-06 Dr. Hajira Jabeen, Prof. Jens Lehmann Outline In the previous lectures we have learned about tensors and factorization methods. RESCAL is a bilinear model for

More information

Neural Networks. Bishop PRML Ch. 5. Alireza Ghane. Feed-forward Networks Network Training Error Backpropagation Applications

Neural Networks. Bishop PRML Ch. 5. Alireza Ghane. Feed-forward Networks Network Training Error Backpropagation Applications Neural Networks Bishop PRML Ch. 5 Alireza Ghane Neural Networks Alireza Ghane / Greg Mori 1 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of

More information

<Special Topics in VLSI> Learning for Deep Neural Networks (Back-propagation)

<Special Topics in VLSI> Learning for Deep Neural Networks (Back-propagation) Learning for Deep Neural Networks (Back-propagation) Outline Summary of Previous Standford Lecture Universal Approximation Theorem Inference vs Training Gradient Descent Back-Propagation

More information

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD WHAT IS A NEURAL NETWORK? The simplest definition of a neural network, more properly referred to as an 'artificial' neural network (ANN), is provided

More information

Machine Learning. Neural Networks

Machine Learning. Neural Networks Machine Learning Neural Networks Bryan Pardo, Northwestern University, Machine Learning EECS 349 Fall 2007 Biological Analogy Bryan Pardo, Northwestern University, Machine Learning EECS 349 Fall 2007 THE

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

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

Artificial Neuron (Perceptron)

Artificial Neuron (Perceptron) 9/6/208 Gradient Descent (GD) Hantao Zhang Deep Learning with Python Reading: https://en.wikipedia.org/wiki/gradient_descent Artificial Neuron (Perceptron) = w T = w 0 0 + + w 2 2 + + w d d where

More information

Artificial Neural Networks. MGS Lecture 2

Artificial Neural Networks. MGS Lecture 2 Artificial Neural Networks MGS 2018 - Lecture 2 OVERVIEW Biological Neural Networks Cell Topology: Input, Output, and Hidden Layers Functional description Cost functions Training ANNs Back-Propagation

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

Neural Networks with Applications to Vision and Language. Feedforward Networks. Marco Kuhlmann

Neural Networks with Applications to Vision and Language. Feedforward Networks. Marco Kuhlmann Neural Networks with Applications to Vision and Language Feedforward Networks Marco Kuhlmann Feedforward networks Linear separability x 2 x 2 0 1 0 1 0 0 x 1 1 0 x 1 linearly separable not linearly separable

More information

Feed-forward Networks Network Training Error Backpropagation Applications. Neural Networks. Oliver Schulte - CMPT 726. Bishop PRML Ch.

Feed-forward Networks Network Training Error Backpropagation Applications. Neural Networks. Oliver Schulte - CMPT 726. Bishop PRML Ch. Neural Networks Oliver Schulte - CMPT 726 Bishop PRML Ch. 5 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of biological plausibility We will

More information

Convolutional Neural Networks

Convolutional Neural Networks Convolutional Neural Networks Books» http://www.deeplearningbook.org/ Books http://neuralnetworksanddeeplearning.com/.org/ reviews» http://www.deeplearningbook.org/contents/linear_algebra.html» http://www.deeplearningbook.org/contents/prob.html»

More information

Artificial Neural Networks

Artificial Neural Networks Artificial Neural Networks Oliver Schulte - CMPT 310 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of biological plausibility We will focus on

More information

CSE 190 Fall 2015 Midterm DO NOT TURN THIS PAGE UNTIL YOU ARE TOLD TO START!!!!

CSE 190 Fall 2015 Midterm DO NOT TURN THIS PAGE UNTIL YOU ARE TOLD TO START!!!! CSE 190 Fall 2015 Midterm DO NOT TURN THIS PAGE UNTIL YOU ARE TOLD TO START!!!! November 18, 2015 THE EXAM IS CLOSED BOOK. Once the exam has started, SORRY, NO TALKING!!! No, you can t even say see ya

More information

Lecture 5 Neural models for NLP

Lecture 5 Neural models for NLP CS546: Machine Learning in NLP (Spring 2018) http://courses.engr.illinois.edu/cs546/ Lecture 5 Neural models for NLP Julia Hockenmaier juliahmr@illinois.edu 3324 Siebel Center Office hours: Tue/Thu 2pm-3pm

More information

CS 6501: Deep Learning for Computer Graphics. Basics of Neural Networks. Connelly Barnes

CS 6501: Deep Learning for Computer Graphics. Basics of Neural Networks. Connelly Barnes CS 6501: Deep Learning for Computer Graphics Basics of Neural Networks Connelly Barnes Overview Simple neural networks Perceptron Feedforward neural networks Multilayer perceptron and properties Autoencoders

More information

Lecture 5: Logistic Regression. Neural Networks

Lecture 5: Logistic Regression. Neural Networks Lecture 5: Logistic Regression. Neural Networks Logistic regression Comparison with generative models Feed-forward neural networks Backpropagation Tricks for training neural networks COMP-652, Lecture

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

Computational statistics

Computational statistics Computational statistics Lecture 3: Neural networks Thierry Denœux 5 March, 2016 Neural networks A class of learning methods that was developed separately in different fields statistics and artificial

More information

ARTIFICIAL INTELLIGENCE. Artificial Neural Networks

ARTIFICIAL INTELLIGENCE. Artificial Neural Networks INFOB2KI 2017-2018 Utrecht University The Netherlands ARTIFICIAL INTELLIGENCE Artificial Neural Networks Lecturer: Silja Renooij These slides are part of the INFOB2KI Course Notes available from www.cs.uu.nl/docs/vakken/b2ki/schema.html

More information

Multilayer Neural Networks

Multilayer Neural Networks Multilayer Neural Networks Multilayer Neural Networks Discriminant function flexibility NON-Linear But with sets of linear parameters at each layer Provably general function approximators for sufficient

More information

CSC321 Lecture 5: Multilayer Perceptrons

CSC321 Lecture 5: Multilayer Perceptrons CSC321 Lecture 5: Multilayer Perceptrons Roger Grosse Roger Grosse CSC321 Lecture 5: Multilayer Perceptrons 1 / 21 Overview Recall the simple neuron-like unit: y output output bias i'th weight w 1 w2 w3

More information

Neural Networks, Computation Graphs. CMSC 470 Marine Carpuat

Neural Networks, Computation Graphs. CMSC 470 Marine Carpuat Neural Networks, Computation Graphs CMSC 470 Marine Carpuat Binary Classification with a Multi-layer Perceptron φ A = 1 φ site = 1 φ located = 1 φ Maizuru = 1 φ, = 2 φ in = 1 φ Kyoto = 1 φ priest = 0 φ

More information

Artificial Neural Networks 2

Artificial Neural Networks 2 CSC2515 Machine Learning Sam Roweis Artificial Neural s 2 We saw neural nets for classification. Same idea for regression. ANNs are just adaptive basis regression machines of the form: y k = j w kj σ(b

More information

DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY

DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY 1 On-line Resources http://neuralnetworksanddeeplearning.com/index.html Online book by Michael Nielsen http://matlabtricks.com/post-5/3x3-convolution-kernelswith-online-demo

More information

Statistical Machine Learning (BE4M33SSU) Lecture 5: Artificial Neural Networks

Statistical Machine Learning (BE4M33SSU) Lecture 5: Artificial Neural Networks Statistical Machine Learning (BE4M33SSU) Lecture 5: Artificial Neural Networks Jan Drchal Czech Technical University in Prague Faculty of Electrical Engineering Department of Computer Science Topics covered

More information

Artificial Neural Network : Training

Artificial Neural Network : Training Artificial Neural Networ : Training Debasis Samanta IIT Kharagpur debasis.samanta.iitgp@gmail.com 06.04.2018 Debasis Samanta (IIT Kharagpur) Soft Computing Applications 06.04.2018 1 / 49 Learning of neural

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others) Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward

More information

Machine Learning and Data Mining. Multi-layer Perceptrons & Neural Networks: Basics. Prof. Alexander Ihler

Machine Learning and Data Mining. Multi-layer Perceptrons & Neural Networks: Basics. Prof. Alexander Ihler + Machine Learning and Data Mining Multi-layer Perceptrons & Neural Networks: Basics Prof. Alexander Ihler Linear Classifiers (Perceptrons) Linear Classifiers a linear classifier is a mapping which partitions

More information

Neural Networks and the Back-propagation Algorithm

Neural Networks and the Back-propagation Algorithm Neural Networks and the Back-propagation Algorithm Francisco S. Melo In these notes, we provide a brief overview of the main concepts concerning neural networks and the back-propagation algorithm. We closely

More information

Cheng Soon Ong & Christian Walder. Canberra February June 2018

Cheng Soon Ong & Christian Walder. Canberra February June 2018 Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 Outlines Overview Introduction Linear Algebra Probability Linear Regression

More information

CSCI567 Machine Learning (Fall 2018)

CSCI567 Machine Learning (Fall 2018) CSCI567 Machine Learning (Fall 2018) Prof. Haipeng Luo U of Southern California Sep 12, 2018 September 12, 2018 1 / 49 Administration GitHub repos are setup (ask TA Chi Zhang for any issues) HW 1 is due

More information

COGS Q250 Fall Homework 7: Learning in Neural Networks Due: 9:00am, Friday 2nd November.

COGS Q250 Fall Homework 7: Learning in Neural Networks Due: 9:00am, Friday 2nd November. COGS Q250 Fall 2012 Homework 7: Learning in Neural Networks Due: 9:00am, Friday 2nd November. For the first two questions of the homework you will need to understand the learning algorithm using the delta

More information

Multilayer Perceptrons and Backpropagation

Multilayer Perceptrons and Backpropagation Multilayer Perceptrons and Backpropagation Informatics 1 CG: Lecture 7 Chris Lucas School of Informatics University of Edinburgh January 31, 2017 (Slides adapted from Mirella Lapata s.) 1 / 33 Reading:

More information

Neural networks COMS 4771

Neural networks COMS 4771 Neural networks COMS 4771 1. Logistic regression Logistic regression Suppose X = R d and Y = {0, 1}. A logistic regression model is a statistical model where the conditional probability function has a

More information

Jakub Hajic Artificial Intelligence Seminar I

Jakub Hajic Artificial Intelligence Seminar I Jakub Hajic Artificial Intelligence Seminar I. 11. 11. 2014 Outline Key concepts Deep Belief Networks Convolutional Neural Networks A couple of questions Convolution Perceptron Feedforward Neural Network

More information

CSC 411 Lecture 10: Neural Networks

CSC 411 Lecture 10: Neural Networks CSC 411 Lecture 10: Neural Networks Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 10-Neural Networks 1 / 35 Inspiration: The Brain Our brain has 10 11

More information

CSC242: Intro to AI. Lecture 21

CSC242: Intro to AI. Lecture 21 CSC242: Intro to AI Lecture 21 Administrivia Project 4 (homeworks 18 & 19) due Mon Apr 16 11:59PM Posters Apr 24 and 26 You need an idea! You need to present it nicely on 2-wide by 4-high landscape pages

More information

Logistic Regression & Neural Networks

Logistic Regression & Neural Networks Logistic Regression & Neural Networks CMSC 723 / LING 723 / INST 725 Marine Carpuat Slides credit: Graham Neubig, Jacob Eisenstein Logistic Regression Perceptron & Probabilities What if we want a probability

More information

Artificial Neural Networks. Edward Gatt

Artificial Neural Networks. Edward Gatt Artificial Neural Networks Edward Gatt What are Neural Networks? Models of the brain and nervous system Highly parallel Process information much more like the brain than a serial computer Learning Very

More information

Artificial Neural Networks

Artificial Neural Networks Introduction ANN in Action Final Observations Application: Poverty Detection Artificial Neural Networks Alvaro J. Riascos Villegas University of los Andes and Quantil July 6 2018 Artificial Neural Networks

More information

Mark Gales October y (x) x 1. x 2 y (x) Inputs. Outputs. x d. y (x) Second Output layer layer. layer.

Mark Gales October y (x) x 1. x 2 y (x) Inputs. Outputs. x d. y (x) Second Output layer layer. layer. University of Cambridge Engineering Part IIB & EIST Part II Paper I0: Advanced Pattern Processing Handouts 4 & 5: Multi-Layer Perceptron: Introduction and Training x y (x) Inputs x 2 y (x) 2 Outputs x

More information

Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis

Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis Introduction to Natural Computation Lecture 9 Multilayer Perceptrons and Backpropagation Peter Lewis 1 / 25 Overview of the Lecture Why multilayer perceptrons? Some applications of multilayer perceptrons.

More information

Neural Networks (Part 1) Goals for the lecture

Neural Networks (Part 1) Goals for the lecture Neural Networks (Part ) Mark Craven and David Page Computer Sciences 760 Spring 208 www.biostat.wisc.edu/~craven/cs760/ Some of the slides in these lectures have been adapted/borrowed from materials developed

More information

Course 395: Machine Learning - Lectures

Course 395: Machine Learning - Lectures Course 395: Machine Learning - Lectures Lecture 1-2: Concept Learning (M. Pantic) Lecture 3-4: Decision Trees & CBC Intro (M. Pantic & S. Petridis) Lecture 5-6: Evaluating Hypotheses (S. Petridis) Lecture

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

Lecture 3 Feedforward Networks and Backpropagation

Lecture 3 Feedforward Networks and Backpropagation Lecture 3 Feedforward Networks and Backpropagation CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago April 3, 2017 Things we will look at today Recap of Logistic Regression

More information

ECE G: Special Topics in Signal Processing: Sparsity, Structure, and Inference

ECE G: Special Topics in Signal Processing: Sparsity, Structure, and Inference ECE 18-898G: Special Topics in Signal Processing: Sparsity, Structure, and Inference Neural Networks: A brief touch Yuejie Chi Department of Electrical and Computer Engineering Spring 2018 1/41 Outline

More information

Artificial Neural Networks D B M G. Data Base and Data Mining Group of Politecnico di Torino. Elena Baralis. Politecnico di Torino

Artificial Neural Networks D B M G. Data Base and Data Mining Group of Politecnico di Torino. Elena Baralis. Politecnico di Torino Artificial Neural Networks Data Base and Data Mining Group of Politecnico di Torino Elena Baralis Politecnico di Torino Artificial Neural Networks Inspired to the structure of the human brain Neurons as

More information

arxiv: v3 [cs.lg] 14 Jan 2018

arxiv: v3 [cs.lg] 14 Jan 2018 A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation Gang Chen Department of Computer Science and Engineering, SUNY at Buffalo arxiv:1610.02583v3 [cs.lg] 14 Jan 2018 1 abstract We describe

More information

Machine Learning. Boris

Machine Learning. Boris Machine Learning Boris Nadion boris@astrails.com @borisnadion @borisnadion boris@astrails.com astrails http://astrails.com awesome web and mobile apps since 2005 terms AI (artificial intelligence)

More information

UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$8:$Supervised$ClassificaDon$ with$support$vector$machine$

UVA$CS$6316$$ $Fall$2015$Graduate:$$ Machine$Learning$$ $ $Lecture$8:$Supervised$ClassificaDon$ with$support$vector$machine$ UVACS6316 Fall2015Graduate: MachineLearning Lecture8:SupervisedClassificaDon withsupportvectormachine 9/30/15 Dr.YanjunQi UniversityofVirginia Departmentof ComputerScience 1 Whereweare?! FivemajorsecHonsofthiscourse

More information

Deep Feedforward Networks

Deep Feedforward Networks Deep Feedforward Networks Liu Yang March 30, 2017 Liu Yang Short title March 30, 2017 1 / 24 Overview 1 Background A general introduction Example 2 Gradient based learning Cost functions Output Units 3

More information

A summary of Deep Learning without Poor Local Minima

A summary of Deep Learning without Poor Local Minima A summary of Deep Learning without Poor Local Minima by Kenji Kawaguchi MIT oral presentation at NIPS 2016 Learning Supervised (or Predictive) learning Learn a mapping from inputs x to outputs y, given

More information

Feedforward Neural Nets and Backpropagation

Feedforward Neural Nets and Backpropagation Feedforward Neural Nets and Backpropagation Julie Nutini University of British Columbia MLRG September 28 th, 2016 1 / 23 Supervised Learning Roadmap Supervised Learning: Assume that we are given the features

More information

Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011!

Artificial Neural Networks and Nonparametric Methods CMPSCI 383 Nov 17, 2011! Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011! 1 Todayʼs lecture" How the brain works (!)! Artificial neural networks! Perceptrons! Multilayer feed-forward networks! Error

More information

Statistical Machine Learning from Data

Statistical Machine Learning from Data January 17, 2006 Samy Bengio Statistical Machine Learning from Data 1 Statistical Machine Learning from Data Multi-Layer Perceptrons Samy Bengio IDIAP Research Institute, Martigny, Switzerland, and Ecole

More information

CSE446: Neural Networks Winter 2015

CSE446: Neural Networks Winter 2015 CSE446: Neural Networks Winter 2015 Luke Ze

More information

CSE 352 (AI) LECTURE NOTES Professor Anita Wasilewska. NEURAL NETWORKS Learning

CSE 352 (AI) LECTURE NOTES Professor Anita Wasilewska. NEURAL NETWORKS Learning CSE 352 (AI) LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Learning Neural Networks Classifier Short Presentation INPUT: classification data, i.e. it contains an classification (class) attribute.

More information

Unit III. A Survey of Neural Network Model

Unit III. A Survey of Neural Network Model Unit III A Survey of Neural Network Model 1 Single Layer Perceptron Perceptron the first adaptive network architecture was invented by Frank Rosenblatt in 1957. It can be used for the classification of

More information

Neural networks. Chapter 20. Chapter 20 1

Neural networks. Chapter 20. Chapter 20 1 Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons Multilayer networks Applications of neural networks Chapter 20 2 Brains 10 11 neurons of > 20 types, 10 14 synapses, 1ms

More information

Lecture 3 Feedforward Networks and Backpropagation

Lecture 3 Feedforward Networks and Backpropagation Lecture 3 Feedforward Networks and Backpropagation CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago April 3, 2017 Things we will look at today Recap of Logistic Regression

More information

Introduction to Neural Networks

Introduction to Neural Networks Introduction to Neural Networks Steve Renals Automatic Speech Recognition ASR Lecture 10 24 February 2014 ASR Lecture 10 Introduction to Neural Networks 1 Neural networks for speech recognition Introduction

More information

CS 4700: Foundations of Artificial Intelligence

CS 4700: Foundations of Artificial Intelligence CS 4700: Foundations of Artificial Intelligence Prof. Bart Selman selman@cs.cornell.edu Machine Learning: Neural Networks R&N 18.7 Intro & perceptron learning 1 2 Neuron: How the brain works # neurons

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others) Machine Learning Neural Networks (slides from Domingos, Pardo, others) Human Brain Neurons Input-Output Transformation Input Spikes Output Spike Spike (= a brief pulse) (Excitatory Post-Synaptic Potential)

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

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others) Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward

More information

Neural networks and optimization

Neural networks and optimization Neural networks and optimization Nicolas Le Roux Criteo 18/05/15 Nicolas Le Roux (Criteo) Neural networks and optimization 18/05/15 1 / 85 1 Introduction 2 Deep networks 3 Optimization 4 Convolutional

More information

Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning

Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Nicolas Thome Prenom.Nom@cnam.fr http://cedric.cnam.fr/vertigo/cours/ml2/ Département Informatique Conservatoire

More information

Lecture 2: Logistic Regression and Neural Networks

Lecture 2: Logistic Regression and Neural Networks 1/23 Lecture 2: and Neural Networks Pedro Savarese TTI 2018 2/23 Table of Contents 1 2 3 4 3/23 Naive Bayes Learn p(x, y) = p(y)p(x y) Training: Maximum Likelihood Estimation Issues? Why learn p(x, y)

More information

Multilayer Neural Networks. (sometimes called Multilayer Perceptrons or MLPs)

Multilayer Neural Networks. (sometimes called Multilayer Perceptrons or MLPs) Multilayer Neural Networks (sometimes called Multilayer Perceptrons or MLPs) Linear separability Hyperplane In 2D: w x + w 2 x 2 + w 0 = 0 Feature x 2 = w w 2 x w 0 w 2 Feature 2 A perceptron can separate

More information

Other Topologies. Y. LeCun: Machine Learning and Pattern Recognition p. 5/3

Other Topologies. Y. LeCun: Machine Learning and Pattern Recognition p. 5/3 Y. LeCun: Machine Learning and Pattern Recognition p. 5/3 Other Topologies The back-propagation procedure is not limited to feed-forward cascades. It can be applied to networks of module with any topology,

More information

Deep Learning Lab Course 2017 (Deep Learning Practical)

Deep Learning Lab Course 2017 (Deep Learning Practical) Deep Learning Lab Course 207 (Deep Learning Practical) Labs: (Computer Vision) Thomas Brox, (Robotics) Wolfram Burgard, (Machine Learning) Frank Hutter, (Neurorobotics) Joschka Boedecker University of

More information

y(x n, w) t n 2. (1)

y(x n, w) t n 2. (1) Network training: Training a neural network involves determining the weight parameter vector w that minimizes a cost function. Given a training set comprising a set of input vector {x n }, n = 1,...N,

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

EVERYTHING YOU NEED TO KNOW TO BUILD YOUR FIRST CONVOLUTIONAL NEURAL NETWORK (CNN)

EVERYTHING YOU NEED TO KNOW TO BUILD YOUR FIRST CONVOLUTIONAL NEURAL NETWORK (CNN) EVERYTHING YOU NEED TO KNOW TO BUILD YOUR FIRST CONVOLUTIONAL NEURAL NETWORK (CNN) TARGETED PIECES OF KNOWLEDGE Linear regression Activation function Multi-Layers Perceptron (MLP) Stochastic Gradient Descent

More information

Data Mining Part 5. Prediction

Data Mining Part 5. Prediction Data Mining Part 5. Prediction 5.5. Spring 2010 Instructor: Dr. Masoud Yaghini Outline How the Brain Works Artificial Neural Networks Simple Computing Elements Feed-Forward Networks Perceptrons (Single-layer,

More information

Radial-Basis Function Networks

Radial-Basis Function Networks Radial-Basis Function etworks A function is radial basis () if its output depends on (is a non-increasing function of) the distance of the input from a given stored vector. s represent local receptors,

More information

Reading Group on Deep Learning Session 1

Reading Group on Deep Learning Session 1 Reading Group on Deep Learning Session 1 Stephane Lathuiliere & Pablo Mesejo 2 June 2016 1/31 Contents Introduction to Artificial Neural Networks to understand, and to be able to efficiently use, the popular

More information

Comments. Assignment 3 code released. Thought questions 3 due this week. Mini-project: hopefully you have started. implement classification algorithms

Comments. Assignment 3 code released. Thought questions 3 due this week. Mini-project: hopefully you have started. implement classification algorithms Neural networks Comments Assignment 3 code released implement classification algorithms use kernels for census dataset Thought questions 3 due this week Mini-project: hopefully you have started 2 Example:

More information

text classification 3: neural networks

text classification 3: neural networks text classification 3: neural networks CS 585, Fall 2018 Introduction to Natural Language Processing http://people.cs.umass.edu/~miyyer/cs585/ Mohit Iyyer College of Information and Computer Sciences University

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

Neural networks. Chapter 19, Sections 1 5 1

Neural networks. Chapter 19, Sections 1 5 1 Neural networks Chapter 19, Sections 1 5 Chapter 19, Sections 1 5 1 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 19, Sections 1 5 2 Brains 10

More information

Deep Learning: a gentle introduction

Deep Learning: a gentle introduction Deep Learning: a gentle introduction Jamal Atif jamal.atif@dauphine.fr PSL, Université Paris-Dauphine, LAMSADE February 8, 206 Jamal Atif (Université Paris-Dauphine) Deep Learning February 8, 206 / Why

More information

Deep Learning. What Is Deep Learning? The Rise of Deep Learning. Long History (in Hind Sight)

Deep Learning. What Is Deep Learning? The Rise of Deep Learning. Long History (in Hind Sight) CSCE 636 Neural Networks Instructor: Yoonsuck Choe Deep Learning What Is Deep Learning? Learning higher level abstractions/representations from data. Motivation: how the brain represents sensory information

More information

ATASS: Word Embeddings

ATASS: Word Embeddings ATASS: Word Embeddings Lee Gao April 22th, 2016 Guideline Bag-of-words (bag-of-n-grams) Today High dimensional, sparse representation dimension reductions LSA, LDA, MNIR Neural networks Backpropagation

More information