Stat 271

Probabilistic Models of the Visual Cortex:
 
Tues/Thurs: 12:30-1:45 pm Fall 2015, Franz 5264.
 
www.stat.ucla.edu/~yuille/Courses/
 

---

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 Material

• Course notes (available on line)
• A.L. Yuille and D.K. Kersten.EarlyVision. Invited Book Chapter. 2015.
  
• Understanding Vision: Theories, Models, and Data, Zhaoping Li. Oxford. 2014
  
• Theortical Neuroscience: P. Dayan and L.F. Abbott. MIT Press 2001. This gives more detailed background on the neuroscience.
  
• Instructor: Prof. Alan Yuille, yuille@stat.ucla.edu, 310-267-5383, office Math Sciences 8967.
• Office Hours: Wednesday 4.00-5.00 pm (8967 Math Sciences), or by appointment (email).
• Syllabus.
  

Grading Plan: 4 homework assignments, 1 final project.
Homework 1:
Due 27/Oct/2015                                                                                                                                                                                                                                                                                                                            Homework 2: Due 17/Nov/2015
Homework 3. Due 15/Dec/2015

Tentative Schedule.

Lecture	Date	Topics	Reading Materials	Handouts
1	Sept-24	Introduction; Guest Lecturer. Dr. Vittal Premachandran	IntroLecture
2	Sept-29	A Walk through the Mammalian Visual System. Prof. C. Reid (Allen Institute) online	Lecture2
3	Oct-01	The Retina and Linear Models of Simplified Cells	RetinaIntroduction	LinearModelsSimplifiedCells
4	Oct-06	Introduction to V1, Simple Cells in V1, Intro to Sparsity	Lecture4 SimpleCellsCortex	LinearFilters LinearFilterKokkinos
5	Oct-08	Sparsity, Matched Filters, Hebbian Learning, Regression	BasisFunctionsSparsity HebbsRegression	SparsityStatistics CurtisBaker
6	Oct-13	Filters Methods for Binoculare Staero and Motion	StereoMotion
7	Oct-15	Probabilites, Decision Theory, and Context	ProbabilitiesDecisions	ContextMarkov
8	Oct-20	Boltzmann Machines	BoltzmannMachines	Online Lectures by G. Hinton
9	Oct-22	Probabilities and Context Review	ContextExamples	Previous Material and YuilleKersten Chapter
10	Oct-27	Context and Attention	AttentionHierarchicalSegmentation	LeeGroupExperimentsSummary
11	Oct 29	Cue Coupling: Directed Graphical Models.	BasicCueCouping CausalCueCoupling	CausalDivisive
12	Nov 3	Motion Perception and Prediction	MotionPhenomena MotionModels	Kalman1 Kalman2 KalmanMotionTracking
13	Nov 5	Perceptrons and Multilayer Perceptrons	Perceptrons MultilayerPerceptronsRegression
14	Nov 10	Deep Networks:  Guest Lecturer. Dr. Vittal Premachandran	DeepNetworksIntro AlexNet	DeepNetsAndRealNeurons
15	Nov 12	Deep Network Example: With context	HumanPose SemanticSegmentation	ModelsVentralStream
16	Nov 17	Compositional Hierarchical Models	CompositionComplexity CompositionLearning	MathsComposition
17	Nov 19	Visual Grammars	ParsingObjects BigPicture
18	Nov 24	Reinforcement Learning	ReinforcementLearning	ReinforcementNotes
19	Dec 1	Recurrent Neural Networks and LSTMs; Guest Lecturer Junhua Mao	CriticalReviewRNNsLSTMs
20	Dec 3	Review of Course