580.691/491 Learning Theory
Course Instructor: Reza Shadmehr


Overview: This course introduces the probabilistic foundations of learning theory. We will discuss topics in regression, estimation, optimal control, system identification, Bayesian learning, and classification. Our aim is to first derive some of the important mathematical results in these topics, and then apply the framework to problems in biology, particularly animal learning and control of action.

 

Lecture times: Spring semester, 2012.

Mondays and Wednesdays, 3:00 – 4:15 PM, Shaffer 302.

Teaching Assistant: Andrew Cheng

Exams: Midterm on March 14, Final to be announced

Suggested Text:  Biological Learning and Control (Shadmehr and Mussa-Ivaldi), MIT Press

 

Useful mathematical identities

 

Course Outline:

            Introduction

          Lecture 1: (intro.ppt) Introduction: adaptation vs. learning; linear classifiers; types of adaptation: supervised, unsupervised, reinforcement.
Homework: digit classification and cross validation

          Lecture 2: Review of probability theory.  Bayes rule, expected value and variance of random variables and sum of random variables, expected value of random variables raised to a power, Binomial distribution, Poisson distribution, Normal distribution.
Homework: probability theory

            Regression, generalization, and maximum likelihood

          Lecture 3: (LMS_1.ppt) Loss function as mean squared error; batch learning and the normal equation; Cross validation, batch vs. online learning, steepest descent algorithm, LMS, convergence of LMS.
Homework: (simulation) classify using regression.  Data set.

          Lecture 4: (LMS_2.ppt) Newton-Raphson, LMS and steepest descent with Newton-Raphson, weighted least-squares, regression with basis functions.
Homework: moving centers of Gaussian bases.

          Lecture 5: (generalization.ppt) generalization function, examples from psychophysics, estimation of generalization function from sequence of errors (linear technique)
Paper to discuss: Poggio T, Fahle M, Edelman S. (1992) Fast perceptual learning in visual hyperacuity.  Science 1992 May 15, 256:1018-21.
Homework: (simulation) estimate generalization function from record of errors.  Data set.

          Lecture 6: (ML_1.ppt) Maximum likelihood estimation; likelihood of data given a distribution; ML estimate of model weights and model noise, integration of multiple sensory data.
Reading: 4.1-4.5 of Shadmehr and Mussa-Ivaldi.
Homework: derive online estimates of model weights and model noise.

 

            State estimation and sensorimotor integration

          Lecture 7:  (Kalmanfilter.ppt) Optimal parameter estimation, parameter uncertainty, state noise and measurement noise, adjusting learning rates to minimize model uncertainty.  Derivation of the Kalman filter algorithm. 
Reading: chapters 4.6 and 4.7 of Shadmehr and Mussa-Ivaldi.
Homework: Convergence of the Kalman gain and uncertainty.

          Lecture 8:  Estimation with multiple sensors, estimation with signal-dependent noise.
Reading: 4.9 and 4.10 of Shadmehr and Mussa-Ivaldi.
Homework

          Bayesian integration

          Lecture 9:  (Bayes_2.ppt) Kalman filter and Bayesian estimation; factorization of joint distribution of Gaussian variables.
Reading: 5.1 of Shadmehr and Mussa-Ivaldi.
Homework: posterior distribution with two observed data points; maximizing the posterior directly.

          Lecture 10:  Causal inference and the problem of deciding between two generative models; the influence of priors in how we make movements and perceive motion; the influence of priors in cognitive decision making.
Reading: 5.2-5.4 of Shadmehr and Mussa-Ivaldi.
Homework

          Lecture 11:  Use of the Kalman gain to account for learning in animals, classical conditioning, Kamin blocking, and backward blocking, with examples of adaptation in people. 
Reading: 5.5, 6.1-6.4.

          Sensorimotor adaptation

          Lecture 12:  A generative model of sensorimotor adaptation experiments; accounting for sensory illusions during adaptation; effect of statistics of prior actions on patterns of learning. 
Reading: 6.5-6.7.

          Lecture 13: Modulating sensitivity to error through manipulation of state and measurement noises; modulating forgetting rates.
Reading: chapter 7.

          Lecture 14:  Multiple timescales of memory.
Reading: chapter 8.
Homework

 

          Structural learning

          Lecture 15:  (SubSpace.ppt) Introduction to subspace analysis; projection of row vectors of matrices, singular value decomposition, system identification of deterministic systems using subspace methods.
Homework: system identification of a deterministic system
Data set
Reading: 9.1-9.6
Overschee and De Moor (1996) Subspace identification for linear systems: theory, implementation, applications.  Kluwer Academic, The Netherlands

          Lecture 16:  Identification of the learner, Expectation maximization as an algorithm for system identification.
Reading: 9.8-9.9

 

          Optimal control of linear stochastic systems

          Lecture 17:  Motor costs and rewards. Movement vigor and encoding of reward.  Muscle tuning functions as a signature of motor costs.
Homework.
Reading: Chapter 10.

          Lecture 18:  Open loop optimal control with cost of time.  Temporal discounting of reward.  Optimizing movement duration with motor and accuracy costs.  Control of saccades as an example of a movement in which cost of time appears to be hyperbolic. 
Reading: Chapter 11.
Project 1: Open Loop Optimal Control

          Lecture 19:  Introduction to optimal feedback control.  Bellman’s equation.
Reading: Chapter 12.
Example of Bellman’s equation

          Lecture 20: Optimal feedback control with signal dependent noise.  Constraint optimization with Lagrange multipliers. Lecture notes on optimal control.
Homework.

          Classification via Bayesian estimation

          Lecture 21:  Introduction to classification; Fisher linear discriminant, classification using posterior probabilities with explicit models of densities, confidence and error bounds of the Bayes classifier, Chernoff error bounds. 
Homework: Bayesian classification of a binary decision

          Lecture 22:  Linear and quadratic decision boundaries.  Equal-variance Gaussian densities (linear discriminant analysis), unequal-variance Gaussian densities (quadratic discriminant analysis), Kernel estimates of density.
Homework: Classification using assumptions of equal and unequal Gaussian distributions; classification using kernel density estimates.

          Lecture 23:  Logistic regression as a method to model posterior probability of class membership as a function of state variables; batch algorithm: Iterative Re-weighted Least Squares; on-line algorithm.
Homework: logistic regression with multiple classes of unequal variance.

 

          Expectation Maximization

          Lecture 24:  Unsupervised classification.  Mixture models, K-means algorithm, and Expectation-Maximization (EM). 
Homework: image segmentation.  Imagedata 

          Lecture 25:  EM and conditional mixtures.  EM as maximizing the expected complete log-likelihood; method of Lagrange multipliers; selecting number of mixture components; mixture of experts.

 

          Reinforcement learning

          Lecture 26:  Introduction to reinforcement learning; value functions and Bellman equations; generalized policy iteration
Homework: rat maze problem. Mazedata .

          Lecture 27:  Temporal difference learning; policy improvement theorem; addiction and reinforcement learning.
Homework.  Randomwalkdata  Schultzpaper

          Lecture 28:  TD-lambda and eligibility trace.