Lecture 3a: The Origin of Variational Bayes
|
|
- Ashlie Melton
- 5 years ago
- Views:
Transcription
1 CSC535: 013 Advanced Machine Learning Lecture 3a: The Origin of Variational Bayes Geoffrey Hinton
2 The origin of variational Bayes In variational Bayes, e approximate the true posterior across parameters by a much simpler, factorial distribution. Since e are being Bayesian, e need a prior for this posterior distribution. When e use standard L eight decay e are implicitly assuming a Gaussian prior ith zero mean. Could e have a more interesting prior?
3 Types of eight penalty Sometimes it orks better to use a eight penalty that has negligible effect on large eights. We can easily make up a heuristic cost function for this. But e get more insight if e vie it as the negative log probability under a mixture of to zero-mean Gaussians C( ) 0 λ = 1+ k 0
4 Soft eight-sharing Le Cun shoed that netorks generalize better if e constrain subsets of the eights to be equal. This removes degrees of freedom from the parameters so it simplifies the model. But for most tasks e do not kno in advance hich eights should be the same. Maybe e can learn hich eights should be the same.
5 Modeling the distribution of the eights The values of the eights form a distribution in a onedimensional space. If the eights are tightly clustered, they have high probability density under a mixture of Gaussians model. To raise the probability density move each eight toards its nearest cluster center. p() W à
6 Fitting the eights and the mixture prior together We can alternate beteen to types of update: Adjust the eights to reduce the error in the output and to increase the probability density of the eights under the mixture prior. Adjust the means and variances and mixing proportions in the mixture prior to fit the posterior distribution of the eights better. This is called empirical Bayes. This automatically clusters the eights. We do not need to specify in advance hich eights should belong to the same cluster.
7 A different optimization method Alternatively, e can just apply conjugate gradient descent to all of the parameters in parallel (hich is hat e did). To keep the variance positive, use the log variances in the optimization (these are the natural parameters for a scale variable). To ensure that the mixing proportions of the Gaussians sum to 1, use the parameters of a softmax in the optimization. x π i = j e i e x j
8 The cost function and its derivatives ) ( ) ( ), ( log ) ( 1 j i j j i c out i j j i i j j c c c out j p i c y c t c y k C p t y k C σ µ σ σ µ π σ = = Probability of eight i under Gaussian j negative log probability of desired output under a Gaussian hose mean is the output of the net posterior probability of Gaussian j given eight i
9 The sunspot prediction problem Predicting the number of sunspots next year is important because they affect eather and communications. The hole time series has less than 400 points and there is no obvious ay to get any more data. So it is orth using computationally expensive methods to get good predictions. The best model produced by statisticians as a combination of to linear autoregressive models that sitched at a particular threshold value. Heavy-tailed eight decay orks better. Soft eight-sharing using a mixture of Gaussians prior orks even better.
10 The eights learned by the eight hidden units for predicting the number of sunspots 1 1 3: 4 fin de siècle Rule 1: (uses units): High if high last year. Rule : High if high 6, 9, or 11 years ago. Rule 3: Lo if lo 1 or 8 ago & high or 3 ago. Rule 4: Lo if high 9 ago and lo 1 or 3 ago
11 The Toronto distribution The mixture of five Gaussians learned for clustering the eights. the skydome Weights near zero are very cheap because they have high density under the empirical prior.
12 Predicting sunspot numbers far into the future by iterating the single year predictions. The net ith soft eightsharing gives the loest errors
13 The problem ith soft eight-sharing It constructs a sensible empirical prior for the eights. But it ignores the fact that some eights need to be coded accurately and others can be very imprecise ithout having much effect on the squared error. A coding frameork needs to model the number of bits required to code the value of a eight and this depends on the precision as ell as the value.
14 Using the variational approach to make Bayesian learning efficient Consider a standard backpropagation netork ith one hidden layer and the squared error function. The full Bayesian approach to learning is: Start ith a prior distribution across all possible eight vectors Multiply the prior for each eight vector by the probability of the observed outputs given that eight vector and then renormalize to get the posterior distribution. Use this posterior distribution over all possible eight vectors for making predictions. This is not feasible for large nets. Can e use a tractable approximation to the posterior?
15 An independence assumption We can approximate the posterior distribution by assuming that it is an axis-aligned Gaussian in eight space. i.e. e give each eight its on posterior variance. Weights that are not very important for minimizing the squared error ill have big variances. This can be interpreted nicely in terms of minimum description length. Weights ith high posterior variances can be communicated in very fe bits This is because e can use lots of entropy to pick a precise value from the posterior, so e get lots of bits back.
16 Communicating a noisy eight First pick a precise value for the eight from its posterior. We ill get back a number of bits equal to the entropy of the eight We could imagine quantizing ith a very small quantization idth to eliminate the infinities. Then code the precise value under the Gaussian prior. This costs a number of bits equal to the crossentropy beteen the posterior and the prior. ( Q( )log P( ) d) ( Q( )logq( ) d) expected number of bits to send eight expected number of bits back
17 The cost of communicating a noisy eight If the sender and receiver agree on a prior distribution, P, for the eights, the cost of communicating a eight ith posterior distribution Q is: KL( Q P) = Q( )log Q( ) P( ) d If the distributions are both Gaussian this cost becomes: KL( Q P) = σ log σ P Q + 1 σ P [ σ σ + ( µ µ ) ] Q P P Q
18 What do noisy eights do to the expected squared error? Consider a linear neuron ith a single input. Let the eight on this input be stochastic The noise variance for the eight gets multiplied by the squared input value and added to the squared error: y < Error < = y x > = < ( x) Error x = ( t Stochastic output of neuron < > = mean of eight distribution x y) > = µ > = ( t xµ xµ + x ) σ + x σ Extra squared error caused by noisy eight
19 Ho to deal ith the non-linearity in the hidden units The noise on the incoming connections to a hidden unit is independent so its variance adds. This Gaussian input noise to a hidden unit turns into non-gaussian output noise, but e can use a big table to find the mean and variance of this non-gaussian noise. The non-gaussian noise coming out of each hidden unit is independent so e can just add up the variances coming into an output unit. σ σ 4 σ σ 1 3
20 The mean and variance of the output of a logistic hidden unit non-gaussian noise out Gaussian noise in
21 The forard table The forard table is indexed by the mean and the variance of the Gaussian total input to a hidden unit. µ in It returns the mean and variance of the non- Gaussian output. This non-gaussian mean and variance is all e need to compute the expected squared error. σin µ σ out out
22 The backard table The backard table is indexed by the mean and variance of the total input. It returns four partial derivatives hich are all e need for backpropagating the derivatives of the squared error to the input à hidden eights. µ µ out in, σ µ out in, µ σ out in, σ σ out in
23 Empirical Bayes: Fitting the prior We can no trade off the precision of the eights against the extra squared error caused by noisy eights. even though the residuals are non-gaussian e can choose to code them using a Gaussian. We can also learn the idth of the prior Gaussian used for coding the eights. We can even have a mixture of Gaussians prior This allos the posterior eights to form clusters Very good for coding lots of zero eights precisely ithout using many bits. Also makes large eights cheap if they are the same as other large eights.
24 Some eights learned by variational bayes output eight bias It learns a fe big positive eights, a fe big negative eights, and lots of zeros. It has found four rules that ork ell. 18 input units Only 105 training cases to train 51 eights
25 The learned empirical prior for the eights The posterior for the eights needs to be Gaussian to make it possible to figure out the extra squared error caused by noisy eights and the cost of coding the noisy eights. The learned prior can be a mixture of Gaussians. This learned prior is a mixture of 5 Gaussians ith 14 parameters
Ways to make neural networks generalize better
Ways to make neural networks generalize better Seminar in Deep Learning University of Tartu 04 / 10 / 2014 Pihel Saatmann Topics Overview of ways to improve generalization Limiting the size of the weights
More informationLogistic Regression. Machine Learning Fall 2018
Logistic Regression Machine Learning Fall 2018 1 Where are e? We have seen the folloing ideas Linear models Learning as loss minimization Bayesian learning criteria (MAP and MLE estimation) The Naïve Bayes
More informationApproximate inference in Energy-Based Models
CSC 2535: 2013 Lecture 3b Approximate inference in Energy-Based Models Geoffrey Hinton Two types of density model Stochastic generative model using directed acyclic graph (e.g. Bayes Net) Energy-based
More informationNeural networks and support vector machines
Neural netorks and support vector machines Perceptron Input x 1 Weights 1 x 2 x 3... x D 2 3 D Output: sgn( x + b) Can incorporate bias as component of the eight vector by alays including a feature ith
More informationMachine Learning: Logistic Regression. Lecture 04
Machine Learning: Logistic Regression Razvan C. Bunescu School of Electrical Engineering and Computer Science bunescu@ohio.edu Supervised Learning Task = learn an (unkon function t : X T that maps input
More informationy(x) = x w + ε(x), (1)
Linear regression We are ready to consider our first machine-learning problem: linear regression. Suppose that e are interested in the values of a function y(x): R d R, here x is a d-dimensional vector-valued
More informationECE521 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 informationLearning Energy-Based Models of High-Dimensional Data
Learning Energy-Based Models of High-Dimensional Data Geoffrey Hinton Max Welling Yee-Whye Teh Simon Osindero www.cs.toronto.edu/~hinton/energybasedmodelsweb.htm Discovering causal structure as a goal
More informationThe 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 informationNetworks of McCulloch-Pitts Neurons
s Lecture 4 Netorks of McCulloch-Pitts Neurons The McCulloch and Pitts (M_P) Neuron x x sgn x n Netorks of M-P Neurons One neuron can t do much on its on, but a net of these neurons x i x i i sgn i ij
More informationArtificial Neural Networks. Part 2
Artificial Neural Netorks Part Artificial Neuron Model Folloing simplified model of real neurons is also knon as a Threshold Logic Unit x McCullouch-Pitts neuron (943) x x n n Body of neuron f out Biological
More informationChapter 3. Systems of Linear Equations: Geometry
Chapter 3 Systems of Linear Equations: Geometry Motiation We ant to think about the algebra in linear algebra (systems of equations and their solution sets) in terms of geometry (points, lines, planes,
More informationNonparametric Bayesian Methods (Gaussian Processes)
[70240413 Statistical Machine Learning, Spring, 2015] Nonparametric Bayesian Methods (Gaussian Processes) Jun Zhu dcszj@mail.tsinghua.edu.cn http://bigml.cs.tsinghua.edu.cn/~jun State Key Lab of Intelligent
More informationSTA 4273H: Sta-s-cal Machine Learning
STA 4273H: Sta-s-cal Machine Learning Russ Salakhutdinov Department of Computer Science! Department of Statistical Sciences! rsalakhu@cs.toronto.edu! h0p://www.cs.utoronto.ca/~rsalakhu/ Lecture 2 In our
More informationAnnouncements Wednesday, September 06
Announcements Wednesday, September 06 WeBWorK due on Wednesday at 11:59pm. The quiz on Friday coers through 1.2 (last eek s material). My office is Skiles 244 and my office hours are Monday, 1 3pm and
More informationMachine 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 informationLecture VIII Dim. Reduction (I)
Lecture VIII Dim. Reduction (I) Contents: Subset Selection & Shrinkage Ridge regression, Lasso PCA, PCR, PLS Lecture VIII: MLSC - Dr. Sethu Viayakumar Data From Human Movement Measure arm movement and
More informationCSC321 Lecture 9: Generalization
CSC321 Lecture 9: Generalization Roger Grosse Roger Grosse CSC321 Lecture 9: Generalization 1 / 26 Overview We ve focused so far on how to optimize neural nets how to get them to make good predictions
More informationCSC2515 Winter 2015 Introduction to Machine Learning. Lecture 2: Linear regression
CSC2515 Winter 2015 Introduction to Machine Learning Lecture 2: Linear regression All lecture slides will be available as.pdf on the course website: http://www.cs.toronto.edu/~urtasun/courses/csc2515/csc2515_winter15.html
More informationHow 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 informationMachine Learning. Lecture 4: Regularization and Bayesian Statistics. Feng Li. https://funglee.github.io
Machine Learning Lecture 4: Regularization and Bayesian Statistics Feng Li fli@sdu.edu.cn https://funglee.github.io School of Computer Science and Technology Shandong University Fall 207 Overfitting Problem
More informationDoes the Wake-sleep Algorithm Produce Good Density Estimators?
Does the Wake-sleep Algorithm Produce Good Density Estimators? Brendan J. Frey, Geoffrey E. Hinton Peter Dayan Department of Computer Science Department of Brain and Cognitive Sciences University of Toronto
More informationCSC 2541: Bayesian Methods for Machine Learning
CSC 2541: Bayesian Methods for Machine Learning Radford M. Neal, University of Toronto, 2011 Lecture 3 More Markov Chain Monte Carlo Methods The Metropolis algorithm isn t the only way to do MCMC. We ll
More informationLarge-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 informationCSC321 Lecture 9: Generalization
CSC321 Lecture 9: Generalization Roger Grosse Roger Grosse CSC321 Lecture 9: Generalization 1 / 27 Overview We ve focused so far on how to optimize neural nets how to get them to make good predictions
More informationECE521 lecture 4: 19 January Optimization, MLE, regularization
ECE521 lecture 4: 19 January 2017 Optimization, MLE, regularization First four lectures Lectures 1 and 2: Intro to ML Probability review Types of loss functions and algorithms Lecture 3: KNN Convexity
More informationLecture 3: More on regularization. Bayesian vs maximum likelihood learning
Lecture 3: More on regularization. Bayesian vs maximum likelihood learning L2 and L1 regularization for linear estimators A Bayesian interpretation of regularization Bayesian vs maximum likelihood fitting
More informationCOS 424: Interacting with Data. Lecturer: Rob Schapire Lecture #15 Scribe: Haipeng Zheng April 5, 2007
COS 424: Interacting ith Data Lecturer: Rob Schapire Lecture #15 Scribe: Haipeng Zheng April 5, 2007 Recapitulation of Last Lecture In linear regression, e need to avoid adding too much richness to the
More informationLecture 4: Types of errors. Bayesian regression models. Logistic regression
Lecture 4: Types of errors. Bayesian regression models. Logistic regression A Bayesian interpretation of regularization Bayesian vs maximum likelihood fitting more generally COMP-652 and ECSE-68, Lecture
More informationSTA 4273H: Statistical Machine Learning
STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 11 Project
More informationLeast Absolute Shrinkage is Equivalent to Quadratic Penalization
Least Absolute Shrinkage is Equivalent to Quadratic Penalization Yves Grandvalet Heudiasyc, UMR CNRS 6599, Université de Technologie de Compiègne, BP 20.529, 60205 Compiègne Cedex, France Yves.Grandvalet@hds.utc.fr
More informationStochastic gradient descent; Classification
Stochastic gradient descent; Classification Steve Renals Machine Learning Practical MLP Lecture 2 28 September 2016 MLP Lecture 2 Stochastic gradient descent; Classification 1 Single Layer Networks MLP
More informationSimple Techniques for Improving SGD. CS6787 Lecture 2 Fall 2017
Simple Techniques for Improving SGD CS6787 Lecture 2 Fall 2017 Step Sizes and Convergence Where we left off Stochastic gradient descent x t+1 = x t rf(x t ; yĩt ) Much faster per iteration than gradient
More informationGRADIENT DESCENT. CSE 559A: Computer Vision GRADIENT DESCENT GRADIENT DESCENT [0, 1] Pr(y = 1) w T x. 1 f (x; θ) = 1 f (x; θ) = exp( w T x)
0 x x x CSE 559A: Computer Vision For Binary Classification: [0, ] f (x; ) = σ( x) = exp( x) + exp( x) Output is interpreted as probability Pr(y = ) x are the log-odds. Fall 207: -R: :30-pm @ Lopata 0
More informationBayesian Support Vector Machines for Feature Ranking and Selection
Bayesian Support Vector Machines for Feature Ranking and Selection written by Chu, Keerthi, Ong, Ghahramani Patrick Pletscher pat@student.ethz.ch ETH Zurich, Switzerland 12th January 2006 Overview 1 Introduction
More informationArtificial 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 informationCSC321 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 informationLECTURE NOTE #NEW 6 PROF. ALAN YUILLE
LECTURE NOTE #NEW 6 PROF. ALAN YUILLE 1. Introduction to Regression Now consider learning the conditional distribution p(y x). This is often easier than learning the likelihood function p(x y) and the
More informationPattern Recognition and Machine Learning
Christopher M. Bishop Pattern Recognition and Machine Learning ÖSpri inger Contents Preface Mathematical notation Contents vii xi xiii 1 Introduction 1 1.1 Example: Polynomial Curve Fitting 4 1.2 Probability
More informationword2vec Parameter Learning Explained
word2vec Parameter Learning Explained Xin Rong ronxin@umich.edu Abstract The word2vec model and application by Mikolov et al. have attracted a great amount of attention in recent two years. The vector
More informationLecture 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 informationParametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a
Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a Some slides are due to Christopher Bishop Limitations of K-means Hard assignments of data points to clusters small shift of a
More informationVote. Vote on timing for night section: Option 1 (what we have now) Option 2. Lecture, 6:10-7:50 25 minute dinner break Tutorial, 8:15-9
Vote Vote on timing for night section: Option 1 (what we have now) Lecture, 6:10-7:50 25 minute dinner break Tutorial, 8:15-9 Option 2 Lecture, 6:10-7 10 minute break Lecture, 7:10-8 10 minute break Tutorial,
More informationConsider this problem. A person s utility function depends on consumption and leisure. Of his market time (the complement to leisure), h t
VI. INEQUALITY CONSTRAINED OPTIMIZATION Application of the Kuhn-Tucker conditions to inequality constrained optimization problems is another very, very important skill to your career as an economist. If
More informationNeural Networks for Machine Learning. Lecture 11a Hopfield Nets
Neural Networks for Machine Learning Lecture 11a Hopfield Nets Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Hopfield Nets A Hopfield net is composed of binary threshold
More informationBayesian Machine Learning
Bayesian Machine Learning Andrew Gordon Wilson ORIE 6741 Lecture 2: Bayesian Basics https://people.orie.cornell.edu/andrew/orie6741 Cornell University August 25, 2016 1 / 17 Canonical Machine Learning
More informationMachine Learning Techniques for Computer Vision
Machine Learning Techniques for Computer Vision Part 2: Unsupervised Learning Microsoft Research Cambridge x 3 1 0.5 0.2 0 0.5 0.3 0 0.5 1 ECCV 2004, Prague x 2 x 1 Overview of Part 2 Mixture models EM
More informationSTA 414/2104: Machine Learning
STA 414/2104: Machine Learning Russ Salakhutdinov Department of Computer Science! Department of Statistics! rsalakhu@cs.toronto.edu! http://www.cs.toronto.edu/~rsalakhu/ Lecture 9 Sequential Data So far
More informationMODULE -4 BAYEIAN LEARNING
MODULE -4 BAYEIAN LEARNING CONTENT Introduction Bayes theorem Bayes theorem and concept learning Maximum likelihood and Least Squared Error Hypothesis Maximum likelihood Hypotheses for predicting probabilities
More informationCSC321 Lecture 18: Learning Probabilistic Models
CSC321 Lecture 18: Learning Probabilistic Models Roger Grosse Roger Grosse CSC321 Lecture 18: Learning Probabilistic Models 1 / 25 Overview So far in this course: mainly supervised learning Language modeling
More informationLogistic 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 informationCSC 578 Neural Networks and Deep Learning
CSC 578 Neural Networks and Deep Learning Fall 2018/19 3. Improving Neural Networks (Some figures adapted from NNDL book) 1 Various Approaches to Improve Neural Networks 1. Cost functions Quadratic Cross
More informationCSC321 Lecture 8: Optimization
CSC321 Lecture 8: Optimization Roger Grosse Roger Grosse CSC321 Lecture 8: Optimization 1 / 26 Overview We ve talked a lot about how to compute gradients. What do we actually do with them? Today s lecture:
More informationCSE 417T: Introduction to Machine Learning. Final Review. Henry Chai 12/4/18
CSE 417T: Introduction to Machine Learning Final Review Henry Chai 12/4/18 Overfitting Overfitting is fitting the training data more than is warranted Fitting noise rather than signal 2 Estimating! "#$
More informationLecture 6. Regression
Lecture 6. Regression Prof. Alan Yuille Summer 2014 Outline 1. Introduction to Regression 2. Binary Regression 3. Linear Regression; Polynomial Regression 4. Non-linear Regression; Multilayer Perceptron
More informationRegression coefficients may even have a different sign from the expected.
Multicolinearity Diagnostics : Some of the diagnostics e have just discussed are sensitive to multicolinearity. For example, e kno that ith multicolinearity, additions and deletions of data cause shifts
More informationWeek 5: Logistic Regression & Neural Networks
Week 5: Logistic Regression & Neural Networks Instructor: Sergey Levine 1 Summary: Logistic Regression In the previous lecture, we covered logistic regression. To recap, logistic regression models and
More informationNeural Networks: Backpropagation
Neural Networks: Backpropagation Machine Learning Fall 2017 Based on slides and material from Geoffrey Hinton, Richard Socher, Dan Roth, Yoav Goldberg, Shai Shalev-Shwartz and Shai Ben-David, and others
More informationCSC242: 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 informationGaussian and Linear Discriminant Analysis; Multiclass Classification
Gaussian and Linear Discriminant Analysis; Multiclass Classification Professor Ameet Talwalkar Slide Credit: Professor Fei Sha Professor Ameet Talwalkar CS260 Machine Learning Algorithms October 13, 2015
More informationThe wake-sleep algorithm for unsupervised neural networks
The wake-sleep algorithm for unsupervised neural networks Geoffrey E Hinton Peter Dayan Brendan J Frey Radford M Neal Department of Computer Science University of Toronto 6 King s College Road Toronto
More informationPreliminaries. Definition: The Euclidean dot product between two vectors is the expression. i=1
90 8 80 7 70 6 60 0 8/7/ Preliminaries Preliminaries Linear models and the perceptron algorithm Chapters, T x + b < 0 T x + b > 0 Definition: The Euclidean dot product beteen to vectors is the expression
More informationCPSC 340: Machine Learning and Data Mining. Sparse Matrix Factorization Fall 2018
CPSC 340: Machine Learning and Data Mining Sparse Matrix Factorization Fall 2018 Last Time: PCA with Orthogonal/Sequential Basis When k = 1, PCA has a scaling problem. When k > 1, have scaling, rotation,
More informationLatent Variable Models
Latent Variable Models Stefano Ermon, Aditya Grover Stanford University Lecture 5 Stefano Ermon, Aditya Grover (AI Lab) Deep Generative Models Lecture 5 1 / 31 Recap of last lecture 1 Autoregressive models:
More informationSTA414/2104 Statistical Methods for Machine Learning II
STA414/2104 Statistical Methods for Machine Learning II Murat A. Erdogdu & David Duvenaud Department of Computer Science Department of Statistical Sciences Lecture 3 Slide credits: Russ Salakhutdinov Announcements
More informationNon-Convex Optimization. CS6787 Lecture 7 Fall 2017
Non-Convex Optimization CS6787 Lecture 7 Fall 2017 First some words about grading I sent out a bunch of grades on the course management system Everyone should have all their grades in Not including paper
More informationECE521 Lecture 7/8. Logistic Regression
ECE521 Lecture 7/8 Logistic Regression Outline Logistic regression (Continue) A single neuron Learning neural networks Multi-class classification 2 Logistic regression The output of a logistic regression
More informationMachine Learning (CSE 446): Neural Networks
Machine Learning (CSE 446): Neural Networks Noah Smith c 2017 University of Washington nasmith@cs.washington.edu November 6, 2017 1 / 22 Admin No Wednesday office hours for Noah; no lecture Friday. 2 /
More informationCPSC 540: Machine Learning
CPSC 540: Machine Learning MCMC and Non-Parametric Bayes Mark Schmidt University of British Columbia Winter 2016 Admin I went through project proposals: Some of you got a message on Piazza. No news is
More informationStatistical learning. Chapter 20, Sections 1 4 1
Statistical learning Chapter 20, Sections 1 4 Chapter 20, Sections 1 4 1 Outline Bayesian learning Maximum a posteriori and maximum likelihood learning Bayes net learning ML parameter learning with complete
More informationInterpreting 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 informationMark 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 informationCSC 411: Lecture 02: Linear Regression
CSC 411: Lecture 02: Linear Regression Richard Zemel, Raquel Urtasun and Sanja Fidler University of Toronto (Most plots in this lecture are from Bishop s book) Zemel, Urtasun, Fidler (UofT) CSC 411: 02-Regression
More informationComparison of Modern Stochastic Optimization Algorithms
Comparison of Modern Stochastic Optimization Algorithms George Papamakarios December 214 Abstract Gradient-based optimization methods are popular in machine learning applications. In large-scale problems,
More informationECE521 week 3: 23/26 January 2017
ECE521 week 3: 23/26 January 2017 Outline Probabilistic interpretation of linear regression - Maximum likelihood estimation (MLE) - Maximum a posteriori (MAP) estimation Bias-variance trade-off Linear
More informationCSC321 Lecture 7: Optimization
CSC321 Lecture 7: Optimization Roger Grosse Roger Grosse CSC321 Lecture 7: Optimization 1 / 25 Overview We ve talked a lot about how to compute gradients. What do we actually do with them? Today s lecture:
More informationBayesian Methods for Machine Learning
Bayesian Methods for Machine Learning CS 584: Big Data Analytics Material adapted from Radford Neal s tutorial (http://ftp.cs.utoronto.ca/pub/radford/bayes-tut.pdf), Zoubin Ghahramni (http://hunch.net/~coms-4771/zoubin_ghahramani_bayesian_learning.pdf),
More information13: Variational inference II
10-708: Probabilistic Graphical Models, Spring 2015 13: Variational inference II Lecturer: Eric P. Xing Scribes: Ronghuo Zheng, Zhiting Hu, Yuntian Deng 1 Introduction We started to talk about variational
More informationData 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 informationNeural 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 informationMachine Learning Basics Lecture 7: Multiclass Classification. Princeton University COS 495 Instructor: Yingyu Liang
Machine Learning Basics Lecture 7: Multiclass Classification Princeton University COS 495 Instructor: Yingyu Liang Example: image classification indoor Indoor outdoor Example: image classification (multiclass)
More informationHow to do backpropagation in a brain. Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto
1 How to do backpropagation in a brain Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto What is wrong with back-propagation? It requires labeled training data. (fixed) Almost
More informationLecture 9: Generalization
Lecture 9: Generalization Roger Grosse 1 Introduction When we train a machine learning model, we don t just want it to learn to model the training data. We want it to generalize to data it hasn t seen
More informationOverfitting, Bias / Variance Analysis
Overfitting, Bias / Variance Analysis Professor Ameet Talwalkar Professor Ameet Talwalkar CS260 Machine Learning Algorithms February 8, 207 / 40 Outline Administration 2 Review of last lecture 3 Basic
More informationDeep Learning for NLP
Deep Learning for NLP CS224N Christopher Manning (Many slides borrowed from ACL 2012/NAACL 2013 Tutorials by me, Richard Socher and Yoshua Bengio) Machine Learning and NLP NER WordNet Usually machine learning
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 informationReading 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 informationNeural Networks. CSE 6363 Machine Learning Vassilis Athitsos Computer Science and Engineering Department University of Texas at Arlington
Neural Networks CSE 6363 Machine Learning Vassilis Athitsos Computer Science and Engineering Department University of Texas at Arlington 1 Perceptrons x 0 = 1 x 1 x 2 z = h w T x Output: z x D A perceptron
More informationNONLINEAR CLASSIFICATION AND REGRESSION. J. Elder CSE 4404/5327 Introduction to Machine Learning and Pattern Recognition
NONLINEAR CLASSIFICATION AND REGRESSION Nonlinear Classification and Regression: Outline 2 Multi-Layer Perceptrons The Back-Propagation Learning Algorithm Generalized Linear Models Radial Basis Function
More information11/3/15. Deep Learning for NLP. Deep Learning and its Architectures. What is Deep Learning? Advantages of Deep Learning (Part 1)
11/3/15 Machine Learning and NLP Deep Learning for NLP Usually machine learning works well because of human-designed representations and input features CS224N WordNet SRL Parser Machine learning becomes
More informationThe simplest kind of unit we consider is a linear-gaussian unit. To
A HIERARCHICAL COMMUNITY OF EXPERTS GEOFFREY E. HINTON BRIAN SALLANS AND ZOUBIN GHAHRAMANI Department of Computer Science University of Toronto Toronto, Ontario, Canada M5S 3H5 fhinton,sallans,zoubing@cs.toronto.edu
More informationUniversität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen. Bayesian Learning. Tobias Scheffer, Niels Landwehr
Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen Bayesian Learning Tobias Scheffer, Niels Landwehr Remember: Normal Distribution Distribution over x. Density function with parameters
More informationMachine 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 informationModeling High-Dimensional Discrete Data with Multi-Layer Neural Networks
Modeling High-Dimensional Discrete Data with Multi-Layer Neural Networks Yoshua Bengio Dept. IRO Université de Montréal Montreal, Qc, Canada, H3C 3J7 bengioy@iro.umontreal.ca Samy Bengio IDIAP CP 592,
More informationSelf Supervised Boosting
Self Supervised Boosting Max Welling, Richard S. Zemel, and Geoffrey E. Hinton Department of omputer Science University of Toronto 1 King s ollege Road Toronto, M5S 3G5 anada Abstract Boosting algorithms
More informationDeep 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 informationMachine Learning Lecture 5
Machine Learning Lecture 5 Linear Discriminant Functions 26.10.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Course Outline Fundamentals Bayes Decision Theory
More informationUnsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation
Cognitive Science 30 (2006) 725 731 Copyright 2006 Cognitive Science Society, Inc. All rights reserved. Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation Geoffrey Hinton,
More informationPart 8: Neural Networks
METU Informatics Institute Min720 Pattern Classification ith Bio-Medical Applications Part 8: Neural Netors - INTRODUCTION: BIOLOGICAL VS. ARTIFICIAL Biological Neural Netors A Neuron: - A nerve cell as
More information