AS.050.375, AS.050.675

Probabilistic Models of the Visual Cortex:
 
Tues/Thurs: 9:00-10:15am Fall 2019, Krieger 170.
 
 

Course Description

The course gives an introduction to computational models of the mammalian visual cortex. It covers topics in low-, mid-, and high-level vision. It briefly discusses the relevant evidence from anatomy, electrophysiology, imaging (e.g., fMRI), and psychophysics. It concentrates on mathematical modelling of these phenomena taking into account recent progress in probabilistic models of computer vision and developments in machine learning.

Reading and Background Material

Grading Plan: 5 homework assignments will be posed on blackboard (roughly biweekly).

Homework 1, submission via Gradescope (Entry Code: 944X7V).
Homework 2.
Homework 3.

Preliminary Schedule (subject to revision)

Lecture Date Topics

Handouts

Required Reading Optional Reading
1

Sept-3

Introduction (Part I)
Slides YuilleKersten (Section 1.1, 1.2, 1.3)
2
Sept-5
Introduction (Part II) - How Biological Vision Can Help AI Vision
Slides
J. Tenenbaum et al. 2017 Bialek   EyeSmarter
  Microprocessor   VisualCrowding
3

Sept-10

Introduction to Retina and Primary Visual Cortex (V1)
Retina V1 V1_Mike_May Lecture by Clay Reid
4
Sept-12
Linear Filtering
Slides YuilleKersten (Section 2.1)
5

Sept-17

Sparsity and Hebbian Learning
Sparsity Hebbian RF YuilleKersten (Section 2.2)
6
Sept-19 Filters for Binocular Stereo and Motion
Figures Slides YuilleKersten (Section 2.4)
7

Sept-24

Regression, Nonlinearity and Neural Networks
Slides YuilleKersten (Section 2.3)Talibi&Baker Zhang2016Poster ZhangPaper
8

Sept-26

Bayesian Decision Theories I Slides YuilleKersten (Section 3.1, 3.2)
9
Oct-1
Bayesian Decision Theories II
Slides1 Slides2 YuilleKersten (Section 3.1, 3.2)
10
Oct-3
Cue Coupling I Slides
Yuille&Buelthoff(1993)
11
Oct-8
Cue Coupling II
Slides
ProbModelsOnGraphs
12
Oct-10
Context and Spatial Interactions Between Neurons I Slides YuilleKersten (Section 4)
13
Oct-15
Context and Spatial Interactions Between Neurons II
Slides
YuilleKersten (Section 4)
14
Oct-17
Boltzmann Machines & More Context Examples
Slides
TS Lee (2014)
15
Oct-22
Motion and Kalman Filter
Slides
16
Oct-24
Bayes Historical Overview
Slides

17
Oct-29
Intro to Deep Nets
Slides
18
Oct-31
Adversarial Machine Learning
Slides
19
Nov-5
Unsupervised Learning
20
Nov-7
Attention (Bottom-Up)
21
Nov-12
Compositionality (I)

22
Nov-14
Compositionality (II)

23
Nov-19
Vision and Language


24
Nov-21
High Level Vision



Nov-26
Thanksgiving


Nov-28
Thanksgiving

25
Dec-3
Kalman Filtering
26
Dec-5
Review of Course