Probabilistic Models of the Visual Cortex:
Tues/Thurs: 9:0010:15am Fall 2019, Krieger 170.
The course gives an introduction to computational models of the mammalian visual cortex. It covers topics in low, mid, and highlevel 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.
Grading Plan: 5 homework assignments will be posed on blackboard (roughly biweekly).
Homework 1, submission via Gradescope (Entry Code: 944X7V).
Homework 2.
Homework 3.
Homework 4.
Homework 5.
Preliminary
Schedule (subject to revision)
Lecture  Date  Topics 
Handouts 
Required Reading  Optional Reading 
1  Sept3 
Introduction (Part I) 
Slides  YuilleKersten (Section
1.1, 1.2, 1.3) 

2 
Sept5 
Introduction (Part II)  How Biological Vision Can Help AI Vision 
Slides 
J. Tenenbaum et al. 2017
Bialek EyeSmarter Microprocessor VisualCrowding 

3 
Sept10 
Introduction to Retina and Primary Visual Cortex (V1) 
Retina V1 V1_Mike_May  Lecture by Clay Reid 

4 
Sept12 
Linear Filtering 
Slides  YuilleKersten (Section 2.1)  
5 
Sept17 
Sparsity and Hebbian Learning 
Sparsity Hebbian RF  YuilleKersten (Section 2.2) 

6 
Sept19  Filters for Binocular Stereo and Motion 
Figures Slides  YuilleKersten (Section 2.4) 

7 
Sept24 
Regression, Nonlinearity and Neural Networks 
Slides  YuilleKersten (Section 2.3)  Talibi&Baker Zhang2016Poster ZhangPaper 
8 
Sept26 
Bayesian Decision Theories I  Slides  YuilleKersten (Section 3.1, 3.2)  
9 
Oct1 
Bayesian Decision Theories II 
Slides1 Slides2  YuilleKersten (Section 3.1, 3.2)  
10 
Oct3 
Cue Coupling I  Slides 
Yuille&Buelthoff(1993)  
11 
Oct8 
Cue Coupling II 
Slides  ProbModelsOnGraphs  
12 
Oct10 
Context and Spatial Interactions Between Neurons I  Slides  YuilleKersten (Section 4) 

13 
Oct15 
Context and Spatial Interactions Between Neurons II 
Slides 
YuilleKersten (Section 4) 

14 
Oct17 
Boltzmann Machines & More Context Examples 
Slides  TS Lee (2014)  
15 
Oct22 
Motion and Kalman Filter 
Slides 

16 
Oct24 
Bayes Historical Overview 
Slides 

17 
Oct29 
Intro to Deep Nets 
Slides 

18 
Oct31 
Adversarial Machine Learning 
Slides  
19 
Nov5 
Interpretable Deep Networks 
Slides  Bolei_Zhou JianyuWang Jason_Yosinski VisualConceptsDeepNets  
20 
Nov7 
Unsupervised Deep Networks 
Slides  BootstrappingDeepNetCueCoupling ChenWei2019 ChenxuLuo.et.al Qiao_CVPR_2018 SmirnakisYuille1994 ZheRen17  
21 
Nov12 
Human/Animal Parsing

Slides  Notes  
22 
Nov14 
Learning by Immagination

Slides  Learning_from_synthetic_animals 

23 
Nov19 
Compositional Models 
Slides 
Notes GeorgeCAPCHAS HongruZhuCogSci2019 CompNets 

24 
Nov21 
Compositional Theory 
Slides  
Nov26 
Thanksgiving 

Nov28 
Thanksgiving 

25 
Dec3 
Analysis by Synthesis 
Slides  Notes  
26 
Dec5 
Review of Course 