AS.050.375, AS.050.675, EN.600.485

Probabilistic Models of the Visual Cortex:
 
Tues/Thurs: 9:00-10:15am Fall 2017, Krieger 111.
 
 

---

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

• Course notes and course readings (posted online).
  
• A.L. Yuille and D.K. Kersten.EarlyVision. Invited Book Chapter in From Neuron to Cognition. 2016. This covers much of the first part of the course.
  

• From Neuron to Cognition: via Computational Neuroscience. MIT Press 2016. Eds. M.A. Arbib and J.J. Bonaiuto. There are many powerpoints available in the suppelmental material online:  https://mitpress.ublish.com/book/neuron-cognition#supplements
  
• Understanding Vision: Theories, Models, and Data. Zhaoping Li. Oxford University Press. 2014. This gives more detailed coverage of some topics in the first part of the course.
  
• Note: the second part of the course is based on recent work and so there is no book reference (just class notes and readings).
• Seeing: The Computational Approach to Biological Vision.  J.P. Frisby and J.V. Stone. (2nd Ed) MIT Press. 2010. Introduces the computational approach to vision but with limited mathematics.
• Stanford tutorials, the engineering website,http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutorial, is a good resource for students with limited statistics background, as it introduces very basic regression, dimension reduction (PCA, ICA)  and vectors.
• Stanford tutorials, http://vision.stanford.edu/teaching/cs231n/2017/ , is a good supplement for the later part of the course, it describes how convolutional network are done and has a lot of codes and examples.
• Center for Brains, Minds, and Machines Woods Hole Summer Course. Ed. E. Hildreth. Links to these lectures will be added when they become available.
  
• Instructor: Prof. Alan Yuille, alan.yuille@jhu.edu, office Clark Hall 324b.
• Office Hours: by appointment (email).
• TA: Donald Li. shipui2005@hotmail.com, office Krieger 119
  
• Office Hours: Tuesday 12-1 (confirm).
  
• Syllabus.
  

Grading Plan: 5 homework assignments.
Homework 1   October 3
Homework 2   October 19
Homework 3   November 2
Homework 4   November 16
Homework 5 December 7

Preliminary Schedule (subject to revision)

Lecture	Date	Topics	Handouts	Suggested Reading
1	Sept-5	Introduction to Vision	IntroLecture	YuilleKersten (Section 1.1, 1.2)
2	Sept-7	The Retina.  Simple Linear Models	RetinaIntro RetinaSmarter	YuilleKersten (Sections 1.3, 2.1)
3	Sept-12	Brief Introduction to V1. Models of Simple and Complex Cells.	V1 SimpleRetina SimpleCortex	YuilleKersten (Sections 1.3,  2.1)
4	Sept-14	Sparsity  and Natural Images	Lincoln Basis Sparsity Handnotes	YuilleKersten (Section 2.2)
5	Sept-19	Hebbian Learning and Regression	HebbsRegression RealNeurons PCAhandout	YuilleKersten (Section 2.3)
6	Sept-21	Filters for Binocular Stereo and Motion	StereoMotion	YuilleKersten (Section 2.4)
7	Sept-26	Making Decisions I: Statistical Edge Detection and Segmentation	ProbabilityDecisionEdges DecisionTheory	YuilleKersten (Section 3.1, 3.2)
8	Sept-28	Making Decisions II: Bayes Decision Theory	DecisionTheory1 DecisionTheory2	YuilleKersten (Section 3.1, 3.2)
9	Oct-3	Probability Models of Neurons and Spatial Interactions  (MFT)	ProbModelsSpatial BackgroundMRFMFTGibbs	YuilleKersten (Section 4)
10	Oct-5	Boltzmann Machines	MLnotes BoltzmannMachines ProbModelsGraphs	YuilleKersten (Section 3.3)
11	Oct-10	Context Examples: Weak Membrane, Associative Field, Stereo	ContextExamples	YuilleKersten (Section 4)
12	Oct-12	Bottom-Up Attention	BoyanSlides	YuilleKersten (Section 4)
13	Oct-17	Cue Coupling	WeakCueCoupling CausalCueCoupling	YuilleKersten (Section 4)
14	Oct-19	Cue Coupling Example & Probability on Graphs	ProbabilityOnGraphs
16	Oct-24	Motion Estimation	HandNotesMotion	LuYuille
17	Oct-26	Motion and Prediction	HandNotesFallOff HandNotesPredict	BurgiEtAl
18	Oct-31	Perceptrons	Perceptrons DecisionsLearning
19	Nov-2	MultiLayer Perceptrons	Regression MultilayerPerceptron
20	Nov-7	Deep Networks (I)	AlexNet LowLevelExamples	DeepNets
21	Nov-9	Deep Networks (II)	DeepNetInternal DeepNetUnderstand	SemanticSegmentation
22	Nov-14	Deep Networks (III)	TextCaptioning SiameseNetworks	LowLevelExamples
23	Nov-16	Deep Networks (IV)
	Nov-21	Thanksgiving
	Nov-23	Thanksgiving
24	Nov-28	High Level Vision	LewisPoggio
25	Nov-30	Vision and Language	TextCaptioning
26	Dec-5	Recurrent Neural Networks and LSTMs:Models of Attention	RCNN_LSTM Attention Word2Vec
27	Dec-7	Review of Course