The Hebb rule Neurons that fire together wire together.
|
|
- Helen Wells
- 5 years ago
- Views:
Transcription
1 Unsupervised learning The Hebb rule Neurons that fire together wire together. PCA RF development with PCA
2 Classical Conditioning and Hebbʼs rule Ear A Nose B Tongue When an axon in cell A is near enough to excite cell B and repeatedly and persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A s efficacy in firing B is increased D. O. Hebb (1949)
3 The generalized Hebb rule: where x i are the inputs, η a learning rate, and y the output is assumed linear: y Results in 2D w1 w2 w3 w4 w5 x 1 x 2 x 3 x 4 x 5
4 Example of Hebb in 2D show simulation w + data points o synaptic weights (Note: here inputs have a mean of zero)
5 On the board: Solve simple linear first order ODE Fixed points and their stability for non linear ODE.
6 In the simplest case, the change in synaptic weight w is: Δw i = ηx i y where x are input vectors and y is the neural response. Assume for simplicity a linear neuron: So we get: y = j Now take an average with respect to the distribution of inputs, get: Δw i = η x i x j w j j w j x j
7 If a small change Δw occurs over a short time Δt then: (in matrix notation) If <x>=0, the correlation matrix Q is the covariance matrix as well. What is then the solution of this simple first order linear ODE? (Show on board)
8 Example in 2D - 4 input vectors: x 1 = 0.8 x 2 = 1.0 x 3 = 1.0 x 4 = show on board calculation of Q Q = What are the eigen-values and eigen-vectors of Q? Qz = λz two solutions z 1 = λ 1 =1.62 z 2 = λ 2 = 0.02
9 This holds in general for: If: Qz i = λ i z i dw dt = ηqw w(t) = N a e ηλ j t z j j j=1 Then: where a j are set by the initial conditions. What does this mean compare to simulation plot.
10 Mathematics of the generalized Hebb rule The change in synaptic weight w is: where x are input vectors and y is the neural response. Assume for simplicity a linear neuron: So we get:
11 Taking an average of the distribution of inputs and using E[x i x j ] = x i x j = Q ij and E[x i ] = x i = µ We obtain
12 In matrix form E[Δw ] = η Q x 0 µj [ ]w ek 1 [ ] w y 0 (µ x 0 ) = η Q k 2 J Where J is a matrix of ones, e is a unit vector in direction (1,1,1 1), and or E[Δw ] = ηq ' w ek 1 Where Q ' = Q k 2 J
13 The equation therefore has the form If k 1 is not zero, this has a fixed point, however it is usually not stable. If k 1 =0 then have:
14 The Hebb rule is unstable how can it be stabilized while preserving its properties? The stabilized Hebb (Oja) rule. w ' i (t +1) = w ' i(t) + Δw i Where w(t) =1 (w + Δw) 2 Normalize Appoximate to first order in Δw: (show on board) Now insert Get:
15 Therefore } y The Oja rule therefore has the form:
16 In matrix form: Average
17 Using this rule the weight vector converges to the eigen-vector of Q with the highest eigen-value. It is often called a principal component or PCA rule. The exact dynamics of the Oja rule have been solved by Wyatt and Elfaldel 1995 Variants of networks that extract several principal components have been proposed (e.g: Sanger 1989)
18 Therefore a stabilized Hebb (Oja neuron) carries out Eigen-vector, or principal component analysis (PCA).
19 Using this rule the weight vector converges to the eigen-vector of Q with the highest eigen-value. It is often called a principal component or PCA rule. Another way to look at this: Where for the Oja rule: At the f.p: So the f.p is an eigen-vector of Q. where λ = y 2 The condition λ = y 2 means that w is normalized. Why? -10 pts bonus question Could there be other choices for β?
20 Show that the Oja rule converges to the state w^2 =1 The Oja rule in matrix form: What is d w 2 dt = d(wt w) dt = 2w T dw dt d w 2 dt = 2ηy 2 (1 w 2 ) Do this in detail, and show stability bonus HW question (15 pt)
21 Show that the f.p of the Oja rule is such that the largest eigen-vector with the largest eigen-value (PC) is stable while others are not (from HKP* pg 202). Start with: Assume w=u a +εu b where u a and u b are eigenvectors with eigen-values λ a,b * HKP = Hertz, Krough, Palmer 1990.
22 Get: d(u a + εu b ) dt Therefore: (show on board) = η( λ a u a + ελ b u b λ a u a ελ a u b ελ b u ) a + O(ε 2 ) That is stable only when λ a > λ b for every b.
23 Finding multiple principal components the Sanger algorithm. Subtract projection onto accounted for subspace (Gram-Schmidt) Standard Oja Normalization
24 Homework 1: 1) For the input vectors: x 1 = x 2 = x 3 = x = x = x 6 = Calculate the correlation matrix, the covariance matrix and the eigen-vectors (30 pts). Draw the points and the direction of the eigen-vectors 2) Simulating Hebb synapses: 2a) Implement a simple Hebb neuron with random 2D input, tilted at an angle, θ=30 o with variances 1 and 3 and mean 0. Show the synaptic weight evolution. (200 patterns at least) 2b) Calculate the correlation matrix of the input data. Find the eigen-values, eigen-vectors of this matrix. Compare to 1a. 2c) Repeat 1a for an Oja neuron, compare to 1b. (70 pts) + bonus questions above (another 25 pt)
25 What did we learn up to here?
26 Visual Pathway Visual Cortex Receptive fields are: Binocular Orientation Selective Area 17 LGN Receptive fields are: Monocular Radially Symmetric Retina light electrical signals
27 Left Right Left Right Response (spikes/sec) Tuning curves
28 Orientation Selectivity Response (spikes/sec) Adult Response (spikes/sec) Adult angle Eye-opening Eye-opening angle
29 Response (spikes/sec) Left Right Right Left angle angle % of cells Rittenhouse et. al. group group
30 First use Hebb/PCA with toy examples then used with more realistic examples
31 Aim get selective neurons using a Hebb/PCA rule Simple example: r r r r
32 Why? The eigen-value equation has the form: Q can be rewritten in the equivalent form: And a possible solution can be written as the sum:
33 Inserting, and by orthogonality get: So for l=0, λ=2, and for l=1, λ=q, for l>1 there is no solution. So either w(r)= const with λ=2 or with λ=q.
34 Orientation selectivity from a natural environment: The Images:
35
36 Natural Images, Noise, and Learning Retina image retinal activity present patches update weights LGN Patches from retinal activity image Cortex Patches from noise
37 Preprocessed images: (fig 5.9) 4 different independent examples Symmetrized means that our originals images were duplicated Rotated to 30,60,90 degrees and added to the data set to make it more rotationally symmetric
38 Response (spikes/sec) Left Right Right Left angle angle % of cells group Rittenhouse et. al group
39 Binocularity simple examples. Q = < x x > < x x > l l l r < x x > < x x > r l r r Q is a 2-eye correlation function. What is the solution of the eigen-value equation: Qw = λw w 1 = w 2 = 1 2 λ 1 = a + b λ 2 = a b +1 1
40 In a simpler case This implies Q ll =Q rr, that is eyes are equivalent. And the cross eye correlation is a scaled version of the one eye correlation. If: Qw = λw then: with w 1 = 1 2 m w 2 = 1 m 2 +m m
41 Positive correlations (η=0.2) Hebb with lower saturation at 0 Negative correlations (η=-0.2)
42 Lets now assume that Q is as above for the 1D selectivity example. Q 2 = Q ηq ηq Q Oscillating Correlated q(1+ η) Anti-correlated q(1 η) Constant 2(1+ η) 2(1 η)
43
44 With 2D space included
45 2 partially overlapping eyes using natural images
46 Orientation selectivity and Ocular Dominance Left Eye Left Synapses Right Eye Right Synapses Left Right No. of Cells PCA Bin 5
47 What did we learned today?
Hebb rule book: 'The Organization of Behavior' Theory about the neural bases of learning
PCA by neurons Hebb rule 1949 book: 'The Organization of Behavior' Theory about the neural bases of learning Learning takes place in synapses. Synapses get modified, they get stronger when the pre- and
More informationOutline. NIP: Hebbian Learning. Overview. Types of Learning. Neural Information Processing. Amos Storkey
Outline NIP: Hebbian Learning Neural Information Processing Amos Storkey 1/36 Overview 2/36 Types of Learning Types of learning, learning strategies Neurophysiology, LTP/LTD Basic Hebb rule, covariance
More informationIterative face image feature extraction with Generalized Hebbian Algorithm and a Sanger-like BCM rule
Iterative face image feature extraction with Generalized Hebbian Algorithm and a Sanger-like BCM rule Clayton Aldern (Clayton_Aldern@brown.edu) Tyler Benster (Tyler_Benster@brown.edu) Carl Olsson (Carl_Olsson@brown.edu)
More informationSynaptic Plasticity. Introduction. Biophysics of Synaptic Plasticity. Functional Modes of Synaptic Plasticity. Activity-dependent synaptic plasticity:
Synaptic Plasticity Introduction Dayan and Abbott (2001) Chapter 8 Instructor: Yoonsuck Choe; CPSC 644 Cortical Networks Activity-dependent synaptic plasticity: underlies learning and memory, and plays
More informationPlasticity and Learning
Chapter 8 Plasticity and Learning 8.1 Introduction Activity-dependent synaptic plasticity is widely believed to be the basic phenomenon underlying learning and memory, and it is also thought to play a
More informationEffect of Correlated LGN Firing Rates on Predictions for Monocular Eye Closure vs Monocular Retinal Inactivation
Effect of Correlated LGN Firing Rates on Predictions for Monocular Eye Closure vs Monocular Retinal Inactivation Brian S. Blais Department of Science and Technology, Bryant University, Smithfield RI and
More informationPrincipal Component Analysis
Principal Component Analysis Yingyu Liang yliang@cs.wisc.edu Computer Sciences Department University of Wisconsin, Madison [based on slides from Nina Balcan] slide 1 Goals for the lecture you should understand
More informationCovariance and Correlation Matrix
Covariance and Correlation Matrix Given sample {x n } N 1, where x Rd, x n = x 1n x 2n. x dn sample mean x = 1 N N n=1 x n, and entries of sample mean are x i = 1 N N n=1 x in sample covariance matrix
More informationHow do biological neurons learn? Insights from computational modelling of
How do biological neurons learn? Insights from computational modelling of neurobiological experiments Lubica Benuskova Department of Computer Science University of Otago, New Zealand Brain is comprised
More informationA. The Hopfield Network. III. Recurrent Neural Networks. Typical Artificial Neuron. Typical Artificial Neuron. Hopfield Network.
Part 3A: Hopfield Network III. Recurrent Neural Networks A. The Hopfield Network 1 2 Typical Artificial Neuron Typical Artificial Neuron connection weights linear combination activation function inputs
More informationLateral organization & computation
Lateral organization & computation review Population encoding & decoding lateral organization Efficient representations that reduce or exploit redundancy Fixation task 1rst order Retinotopic maps Log-polar
More informationSlide10. Haykin Chapter 8: Principal Components Analysis. Motivation. Principal Component Analysis: Variance Probe
Slide10 Motivation Haykin Chapter 8: Principal Coponents Analysis 1.6 1.4 1.2 1 0.8 cloud.dat 0.6 CPSC 636-600 Instructor: Yoonsuck Choe Spring 2015 0.4 0.2 0 0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 How can we
More informationTable of Contents EQ EQ EQ EQ EQ EQ KOHONEN...70 EQ STEPHEN GROSSBERG...70 EQ EQ.11...
able of Contents CHAPER VI- HEBBIAN LEARNING AND PRINCIPAL COMPONEN ANALYSIS...3 1. INRODUCION...4 2. EFFEC OF HE HEBB UPDAE...5 3. OJA S RULE...16 4. PRINCIPAL COMPONEN ANALYSIS...20 5. ANI-HEBBIAN LEARNING...27
More informationA. The Hopfield Network. III. Recurrent Neural Networks. Typical Artificial Neuron. Typical Artificial Neuron. Hopfield Network.
III. Recurrent Neural Networks A. The Hopfield Network 2/9/15 1 2/9/15 2 Typical Artificial Neuron Typical Artificial Neuron connection weights linear combination activation function inputs output net
More informationIntroduction to Neural Networks
Introduction to Neural Networks What are (Artificial) Neural Networks? Models of the brain and nervous system Highly parallel Process information much more like the brain than a serial computer Learning
More informationFinancial Informatics XVII:
Financial Informatics XVII: Unsupervised Learning Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-, IRELAND November 9 th, 8. https://www.cs.tcd.ie/khurshid.ahmad/teaching.html
More informationPCA & 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 informationPCA, Kernel PCA, ICA
PCA, Kernel PCA, ICA Learning Representations. Dimensionality Reduction. Maria-Florina Balcan 04/08/2015 Big & High-Dimensional Data High-Dimensions = Lot of Features Document classification Features per
More informationLecture 13. Principal Component Analysis. Brett Bernstein. April 25, CDS at NYU. Brett Bernstein (CDS at NYU) Lecture 13 April 25, / 26
Principal Component Analysis Brett Bernstein CDS at NYU April 25, 2017 Brett Bernstein (CDS at NYU) Lecture 13 April 25, 2017 1 / 26 Initial Question Intro Question Question Let S R n n be symmetric. 1
More informationCS281 Section 4: Factor Analysis and PCA
CS81 Section 4: Factor Analysis and PCA Scott Linderman At this point we have seen a variety of machine learning models, with a particular emphasis on models for supervised learning. In particular, we
More informationHierarchy. Will Penny. 24th March Hierarchy. Will Penny. Linear Models. Convergence. Nonlinear Models. References
24th March 2011 Update Hierarchical Model Rao and Ballard (1999) presented a hierarchical model of visual cortex to show how classical and extra-classical Receptive Field (RF) effects could be explained
More informationLearning and Meta-learning
Learning and Meta-learning computation making predictions choosing actions acquiring episodes statistics algorithm gradient ascent (eg of the likelihood) correlation Kalman filtering implementation Hebbian
More informationNeuroscience Introduction
Neuroscience Introduction The brain As humans, we can identify galaxies light years away, we can study particles smaller than an atom. But we still haven t unlocked the mystery of the three pounds of matter
More informationAS Elementary Cybernetics. Lecture 4: Neocybernetic Basic Models
AS-74.4192 Elementary Cybernetics Lecture 4: Neocybernetic Basic Models Starting point when modeling real complex systems: Observation: Bottom-up approaches (studying the mechanisms alone) is futile Another
More informationUnsupervised Learning
2018 EE448, Big Data Mining, Lecture 7 Unsupervised Learning Weinan Zhang Shanghai Jiao Tong University http://wnzhang.net http://wnzhang.net/teaching/ee448/index.html ML Problem Setting First build and
More informationTuning tuning curves. So far: Receptive fields Representation of stimuli Population vectors. Today: Contrast enhancment, cortical processing
Tuning tuning curves So far: Receptive fields Representation of stimuli Population vectors Today: Contrast enhancment, cortical processing Firing frequency N 3 s max (N 1 ) = 40 o N4 N 1 N N 5 2 s max
More informationLeo Kadanoff and 2d XY Models with Symmetry-Breaking Fields. renormalization group study of higher order gradients, cosines and vortices
Leo Kadanoff and d XY Models with Symmetry-Breaking Fields renormalization group study of higher order gradients, cosines and vortices Leo Kadanoff and Random Matrix Theory Non-Hermitian Localization in
More informationGI07/COMPM012: Mathematical Programming and Research Methods (Part 2) 2. Least Squares and Principal Components Analysis. Massimiliano Pontil
GI07/COMPM012: Mathematical Programming and Research Methods (Part 2) 2. Least Squares and Principal Components Analysis Massimiliano Pontil 1 Today s plan SVD and principal component analysis (PCA) Connection
More informationNeuron Grids as seen as. Elastic Systems. Heikki Hyötyniemi TKK / Control Engineering Presentation at NeuroCafé March 31, 2006
Neuron Grids as seen as Elastic Systems Heikki Hyötyniemi KK / Control Engineering Presentation at NeuroCafé March 31, 2006 Heikki Hyötyniemi Chairman of the Finnish Artificial Intelligence Society (FAIS)
More informationCSE/NB 528 Final Lecture: All Good Things Must. CSE/NB 528: Final Lecture
CSE/NB 528 Final Lecture: All Good Things Must 1 Course Summary Where have we been? Course Highlights Where do we go from here? Challenges and Open Problems Further Reading 2 What is the neural code? What
More informationClustering VS Classification
MCQ Clustering VS Classification 1. What is the relation between the distance between clusters and the corresponding class discriminability? a. proportional b. inversely-proportional c. no-relation Ans:
More informationA MEAN FIELD THEORY OF LAYER IV OF VISUAL CORTEX AND ITS APPLICATION TO ARTIFICIAL NEURAL NETWORKS*
683 A MEAN FIELD THEORY OF LAYER IV OF VISUAL CORTEX AND ITS APPLICATION TO ARTIFICIAL NEURAL NETWORKS* Christopher L. Scofield Center for Neural Science and Physics Department Brown University Providence,
More informationSupporting Online Material for
www.sciencemag.org/cgi/content/full/319/5869/1543/dc1 Supporting Online Material for Synaptic Theory of Working Memory Gianluigi Mongillo, Omri Barak, Misha Tsodyks* *To whom correspondence should be addressed.
More informationPCA and LDA. Man-Wai MAK
PCA and LDA Man-Wai MAK Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University enmwmak@polyu.edu.hk http://www.eie.polyu.edu.hk/ mwmak References: S.J.D. Prince,Computer
More informationLecture 10: Dimension Reduction Techniques
Lecture 10: Dimension Reduction Techniques Radu Balan Department of Mathematics, AMSC, CSCAMM and NWC University of Maryland, College Park, MD April 17, 2018 Input Data It is assumed that there is a set
More informationArtificial Neural Networks Examination, March 2004
Artificial Neural Networks Examination, March 2004 Instructions There are SIXTY questions (worth up to 60 marks). The exam mark (maximum 60) will be added to the mark obtained in the laborations (maximum
More informationPrincipal Components Analysis and Unsupervised Hebbian Learning
Princial Comonents Analysis and Unsuervised Hebbian Learning Robert Jacobs Deartment of Brain & Cognitive Sciences University of Rochester Rochester, NY 1467, USA August 8, 008 Reference: Much of the material
More informationNatural Image Statistics
Natural Image Statistics A probabilistic approach to modelling early visual processing in the cortex Dept of Computer Science Early visual processing LGN V1 retina From the eye to the primary visual cortex
More informationTime-Skew Hebb Rule in a Nonisopotential Neuron
Time-Skew Hebb Rule in a Nonisopotential Neuron Barak A. Pearlmutter To appear (1995) in Neural Computation, 7(4) 76 712 Abstract In an isopotential neuron with rapid response, it has been shown that the
More informationLecture 14 Population dynamics and associative memory; stable learning
Lecture 14 Population dynamics and associative memory; stable learning -Introduction -Associative Memory -Dense networks (mean-ield) -Population dynamics and Associative Memory -Discussion Systems or computing
More informationMachine Learning - MT & 14. PCA and MDS
Machine Learning - MT 2016 13 & 14. PCA and MDS Varun Kanade University of Oxford November 21 & 23, 2016 Announcements Sheet 4 due this Friday by noon Practical 3 this week (continue next week if necessary)
More informationDimension Reduction Techniques. Presented by Jie (Jerry) Yu
Dimension Reduction Techniques Presented by Jie (Jerry) Yu Outline Problem Modeling Review of PCA and MDS Isomap Local Linear Embedding (LLE) Charting Background Advances in data collection and storage
More informationREPORT DOCUMENTATION PAGE
, UNCLASSIFIED SECURITY CLASSIFICATION OF THIS PAGE j?5 REPORT DOCUMENTATION PAGE la. REPORT SECURITY CLASSIFICATION Unclassified 2a. SECURITY CLASSIFICATION AUTHORITY 2b. DECLASSIFICAHON/DOWNGRADING SCHEDULE
More informationDo Neurons Process Information Efficiently?
Do Neurons Process Information Efficiently? James V Stone, University of Sheffield Claude Shannon, 1916-2001 Nothing in biology makes sense except in the light of evolution. Theodosius Dobzhansky, 1973.
More information15 Grossberg Network 1
Grossberg Network Biological Motivation: Vision Bipolar Cell Amacrine Cell Ganglion Cell Optic Nerve Cone Light Lens Rod Horizontal Cell Retina Optic Nerve Fiber Eyeball and Retina Layers of Retina The
More informationNonlinear reverse-correlation with synthesized naturalistic noise
Cognitive Science Online, Vol1, pp1 7, 2003 http://cogsci-onlineucsdedu Nonlinear reverse-correlation with synthesized naturalistic noise Hsin-Hao Yu Department of Cognitive Science University of California
More informationIntroduction to Machine Learning
10-701 Introduction to Machine Learning PCA Slides based on 18-661 Fall 2018 PCA Raw data can be Complex, High-dimensional To understand a phenomenon we measure various related quantities If we knew what
More informationJan 16: The Visual System
Geometry of Neuroscience Matilde Marcolli & Doris Tsao Jan 16: The Visual System References for this lecture 1977 Hubel, D. H., Wiesel, T. N., Ferrier lecture 2010 Freiwald, W., Tsao, DY. Functional compartmentalization
More informationÂngelo Cardoso 27 May, Symbolic and Sub-Symbolic Learning Course Instituto Superior Técnico
BIOLOGICALLY INSPIRED COMPUTER MODELS FOR VISUAL RECOGNITION Ângelo Cardoso 27 May, 2010 Symbolic and Sub-Symbolic Learning Course Instituto Superior Técnico Index Human Vision Retinal Ganglion Cells Simple
More informationCHALMERS, GÖTEBORGS UNIVERSITET. EXAM for ARTIFICIAL NEURAL NETWORKS. COURSE CODES: FFR 135, FIM 720 GU, PhD
CHALMERS, GÖTEBORGS UNIVERSITET EXAM for ARTIFICIAL NEURAL NETWORKS COURSE CODES: FFR 135, FIM 72 GU, PhD Time: Place: Teachers: Allowed material: Not allowed: October 23, 217, at 8 3 12 3 Lindholmen-salar
More informationMachine Learning (CSE 446): Unsupervised Learning: K-means and Principal Component Analysis
Machine Learning (CSE 446): Unsupervised Learning: K-means and Principal Component Analysis Sham M Kakade c 2019 University of Washington cse446-staff@cs.washington.edu 0 / 10 Announcements Please do Q1
More informationPrincipal Component Analysis CS498
Principal Component Analysis CS498 Today s lecture Adaptive Feature Extraction Principal Component Analysis How, why, when, which A dual goal Find a good representation The features part Reduce redundancy
More information(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 informationCOMS 4721: Machine Learning for Data Science Lecture 19, 4/6/2017
COMS 4721: Machine Learning for Data Science Lecture 19, 4/6/2017 Prof. John Paisley Department of Electrical Engineering & Data Science Institute Columbia University PRINCIPAL COMPONENT ANALYSIS DIMENSIONALITY
More informationPrincipal Component Analysis and Linear Discriminant Analysis
Principal Component Analysis and Linear Discriminant Analysis Ying Wu Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208 http://www.eecs.northwestern.edu/~yingwu 1/29
More informationRepresentation Learning in Sensory Cortex: a theory
CBMM Memo No. 026 November 14, 2014 Representation Learning in Sensory Cortex: a theory by Fabio Anselmi, and Tomaso Armando Poggio, Center for Brains, Minds and Machines, McGovern Institute, Massachusetts
More informationThe Role of Weight Normalization in Competitive Learning
Communicated by Todd Leen The Role of Weight Normalization in Competitive Learning Geoffrey J. Goodhill University of Edinburgh, Centre for Cognitive Science, 2 Buccleiich Place, Edinburgh EH8 9LW, United
More informationDeriving Principal Component Analysis (PCA)
-0 Mathematical Foundations for Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Deriving Principal Component Analysis (PCA) Matt Gormley Lecture 11 Oct.
More informationHigher Processing of Visual Information: Lecture II --- April 4, 2007 by Mu-ming Poo
Higher Processing of Visual Information: Lecture II April 4, 2007 by Muming Poo 1. Organization of Mammalian Visual Cortices 2. Structure of the Primary Visual Cortex layering, inputs, outputs, cell types
More informationSTA 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 informationNeural Networks. Fundamentals of Neural Networks : Architectures, Algorithms and Applications. L, Fausett, 1994
Neural Networks Neural Networks Fundamentals of Neural Networks : Architectures, Algorithms and Applications. L, Fausett, 1994 An Introduction to Neural Networks (nd Ed). Morton, IM, 1995 Neural Networks
More informationPCA and LDA. Man-Wai MAK
PCA and LDA Man-Wai MAK Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University enmwmak@polyu.edu.hk http://www.eie.polyu.edu.hk/ mwmak References: S.J.D. Prince,Computer
More informationEXTENSIONS OF ICA AS MODELS OF NATURAL IMAGES AND VISUAL PROCESSING. Aapo Hyvärinen, Patrik O. Hoyer and Jarmo Hurri
EXTENSIONS OF ICA AS MODELS OF NATURAL IMAGES AND VISUAL PROCESSING Aapo Hyvärinen, Patrik O. Hoyer and Jarmo Hurri Neural Networks Research Centre Helsinki University of Technology P.O. Box 5400, FIN-02015
More informationMaster Recherche IAC TC2: Apprentissage Statistique & Optimisation
Master Recherche IAC TC2: Apprentissage Statistique & Optimisation Alexandre Allauzen Anne Auger Michèle Sebag LIMSI LRI Oct. 4th, 2012 This course Bio-inspired algorithms Classical Neural Nets History
More informationManifold Learning for Signal and Visual Processing Lecture 9: Probabilistic PCA (PPCA), Factor Analysis, Mixtures of PPCA
Manifold Learning for Signal and Visual Processing Lecture 9: Probabilistic PCA (PPCA), Factor Analysis, Mixtures of PPCA Radu Horaud INRIA Grenoble Rhone-Alpes, France Radu.Horaud@inria.fr http://perception.inrialpes.fr/
More informationStatistical Machine Learning
Statistical Machine Learning Christoph Lampert Spring Semester 2015/2016 // Lecture 12 1 / 36 Unsupervised Learning Dimensionality Reduction 2 / 36 Dimensionality Reduction Given: data X = {x 1,..., x
More informationMachine Learning. Dimensionality reduction. Hamid Beigy. Sharif University of Technology. Fall 1395
Machine Learning Dimensionality reduction Hamid Beigy Sharif University of Technology Fall 1395 Hamid Beigy (Sharif University of Technology) Machine Learning Fall 1395 1 / 47 Table of contents 1 Introduction
More informationAdaptation in the Neural Code of the Retina
Adaptation in the Neural Code of the Retina Lens Retina Fovea Optic Nerve Optic Nerve Bottleneck Neurons Information Receptors: 108 95% Optic Nerve 106 5% After Polyak 1941 Visual Cortex ~1010 Mean Intensity
More informationarxiv: v1 [q-bio.nc] 4 Jan 2016
Nonlinear Hebbian learning as a unifying principle in receptive field formation Carlos S. N. Brito*, Wulfram Gerstner arxiv:1601.00701v1 [q-bio.nc] 4 Jan 2016 School of Computer and Communication Sciences
More informationECE 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 informationSynaptic Input. Linear Model of Synaptic Transmission. Professor David Heeger. September 5, 2000
Synaptic Input Professor David Heeger September 5, 2000 The purpose of this handout is to go a bit beyond the discussion in Ch. 6 of The Book of Genesis on synaptic input, and give some examples of how
More informationExercises * on Principal Component Analysis
Exercises * on Principal Component Analysis Laurenz Wiskott Institut für Neuroinformatik Ruhr-Universität Bochum, Germany, EU 4 February 207 Contents Intuition 3. Problem statement..........................................
More informationMODELS OF LEARNING AND THE POLAR DECOMPOSITION OF BOUNDED LINEAR OPERATORS
Eighth Mississippi State - UAB Conference on Differential Equations and Computational Simulations. Electronic Journal of Differential Equations, Conf. 19 (2010), pp. 31 36. ISSN: 1072-6691. URL: http://ejde.math.txstate.edu
More informationFactor Analysis (10/2/13)
STA561: Probabilistic machine learning Factor Analysis (10/2/13) Lecturer: Barbara Engelhardt Scribes: Li Zhu, Fan Li, Ni Guan Factor Analysis Factor analysis is related to the mixture models we have studied.
More informationCSC 411 Lecture 12: Principal Component Analysis
CSC 411 Lecture 12: Principal Component Analysis Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 12-PCA 1 / 23 Overview Today we ll cover the first unsupervised
More information+ + ( + ) = Linear recurrent networks. Simpler, much more amenable to analytic treatment E.g. by choosing
Linear recurrent networks Simpler, much more amenable to analytic treatment E.g. by choosing + ( + ) = Firing rates can be negative Approximates dynamics around fixed point Approximation often reasonable
More informationNeuroinformatics. Marcus Kaiser. Week 10: Cortical maps and competitive population coding (textbook chapter 7)!
0 Neuroinformatics Marcus Kaiser Week 10: Cortical maps and competitive population coding (textbook chapter 7)! Outline Topographic maps Self-organizing maps Willshaw & von der Malsburg Kohonen Dynamic
More informationUnsupervised learning: beyond simple clustering and PCA
Unsupervised learning: beyond simple clustering and PCA Liza Rebrova Self organizing maps (SOM) Goal: approximate data points in R p by a low-dimensional manifold Unlike PCA, the manifold does not have
More informationClassification. The goal: map from input X to a label Y. Y has a discrete set of possible values. We focused on binary Y (values 0 or 1).
Regression and PCA Classification The goal: map from input X to a label Y. Y has a discrete set of possible values We focused on binary Y (values 0 or 1). But we also discussed larger number of classes
More informationNoisy Streaming PCA. Noting g t = x t x t, rearranging and dividing both sides by 2η we get
Supplementary Material A. Auxillary Lemmas Lemma A. Lemma. Shalev-Shwartz & Ben-David,. Any update of the form P t+ = Π C P t ηg t, 3 for an arbitrary sequence of matrices g, g,..., g, projection Π C onto
More informationComputational Neuroscience. Structure Dynamics Implementation Algorithm Computation - Function
Computational Neuroscience Structure Dynamics Implementation Algorithm Computation - Function Learning at psychological level Classical conditioning Hebb's rule When an axon of cell A is near enough to
More informationDeep Learning Basics Lecture 7: Factor Analysis. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 7: Factor Analysis Princeton University COS 495 Instructor: Yingyu Liang Supervised v.s. Unsupervised Math formulation for supervised learning Given training data x i, y i
More informationData Mining. Dimensionality reduction. Hamid Beigy. Sharif University of Technology. Fall 1395
Data Mining Dimensionality reduction Hamid Beigy Sharif University of Technology Fall 1395 Hamid Beigy (Sharif University of Technology) Data Mining Fall 1395 1 / 42 Outline 1 Introduction 2 Feature selection
More informationNeural Network Training
Neural Network Training Sargur Srihari Topics in Network Training 0. Neural network parameters Probabilistic problem formulation Specifying the activation and error functions for Regression Binary classification
More informationThe functional organization of the visual cortex in primates
The functional organization of the visual cortex in primates Dominated by LGN M-cell input Drosal stream for motion perception & spatial localization V5 LIP/7a V2 V4 IT Ventral stream for object recognition
More informationGatsby Theoretical Neuroscience Lectures: Non-Gaussian statistics and natural images Parts I-II
Gatsby Theoretical Neuroscience Lectures: Non-Gaussian statistics and natural images Parts I-II Gatsby Unit University College London 27 Feb 2017 Outline Part I: Theory of ICA Definition and difference
More informationRobot Image Credit: Viktoriya Sukhanova 123RF.com. Dimensionality Reduction
Robot Image Credit: Viktoriya Sukhanova 13RF.com Dimensionality Reduction Feature Selection vs. Dimensionality Reduction Feature Selection (last time) Select a subset of features. When classifying novel
More informationCell division takes place next to the RPE. Neuroblastic cells have the capacity to differentiate into any of the cell types found in the mature retina
RPE is a monolayer of hexagonal shaped neural epithelial cells that have the same embryological origin as the neural retina. They mature before the neural retina and play a key role in metabolic support
More informationHopfield Neural Network and Associative Memory. Typical Myelinated Vertebrate Motoneuron (Wikipedia) Topic 3 Polymers and Neurons Lecture 5
Hopfield Neural Network and Associative Memory Typical Myelinated Vertebrate Motoneuron (Wikipedia) PHY 411-506 Computational Physics 2 1 Wednesday, March 5 1906 Nobel Prize in Physiology or Medicine.
More informationNeuron. Detector Model. Understanding Neural Components in Detector Model. Detector vs. Computer. Detector. Neuron. output. axon
Neuron Detector Model 1 The detector model. 2 Biological properties of the neuron. 3 The computational unit. Each neuron is detecting some set of conditions (e.g., smoke detector). Representation is what
More informationDimensionality Reduction
Lecture 5 1 Outline 1. Overview a) What is? b) Why? 2. Principal Component Analysis (PCA) a) Objectives b) Explaining variability c) SVD 3. Related approaches a) ICA b) Autoencoders 2 Example 1: Sportsball
More informationAdvanced Introduction to Machine Learning
10-715 Advanced Introduction to Machine Learning Homework 3 Due Nov 12, 10.30 am Rules 1. Homework is due on the due date at 10.30 am. Please hand over your homework at the beginning of class. Please see
More informationComputational Explorations in Cognitive Neuroscience Chapter 2
Computational Explorations in Cognitive Neuroscience Chapter 2 2.4 The Electrophysiology of the Neuron Some basic principles of electricity are useful for understanding the function of neurons. This is
More informationOptimal In-Place Self-Organization for Cortical Development: Limited Cells, Sparse Coding and Cortical Topography
Optimal In-Place Self-Organization for Cortical Development: Limited Cells, Sparse Coding and Cortical Topography Juyang Weng and Matthew D. Luciw Department of Computer Science and Engineering Michigan
More informationLast updated: Oct 22, 2012 LINEAR CLASSIFIERS. J. Elder CSE 4404/5327 Introduction to Machine Learning and Pattern Recognition
Last updated: Oct 22, 2012 LINEAR CLASSIFIERS Problems 2 Please do Problem 8.3 in the textbook. We will discuss this in class. Classification: Problem Statement 3 In regression, we are modeling the relationship
More informationSTA 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 informationConsider the following spike trains from two different neurons N1 and N2:
About synchrony and oscillations So far, our discussions have assumed that we are either observing a single neuron at a, or that neurons fire independent of each other. This assumption may be correct in
More informationLinear Dimensionality Reduction
Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Principal Component Analysis 3 Factor Analysis
More informationProbabilistic & Unsupervised Learning
Probabilistic & Unsupervised Learning Week 2: Latent Variable Models Maneesh Sahani maneesh@gatsby.ucl.ac.uk Gatsby Computational Neuroscience Unit, and MSc ML/CSML, Dept Computer Science University College
More informationTutorial on Blind Source Separation and Independent Component Analysis
Tutorial on Blind Source Separation and Independent Component Analysis Lucas Parra Adaptive Image & Signal Processing Group Sarnoff Corporation February 09, 2002 Linear Mixtures... problem statement...
More information