AS.050.375, AS.050.675, EN.600.485

Probabilistic Models of the Visual Cortex:
 
Tues/Thurs: 9:00-10:15am Fall 2018, 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.
• TA: Chenxi Liu, cxliu@jhu.edu, office Malone 260.
  
• Office Hours: by email appointment.
  
• Syllabus.
  

Grading Plan: 5 homework assignments.

Preliminary Schedule (subject to revision)

Lecture	Date	Topics	Handouts	Suggested Reading
1	Sept-4	Introduction to Vision	Slides	YuilleKersten (Section 1.1, 1.2)
2	Sept-6	The Retina.  Simple Linear Models	Slides	YuilleKersten (Sections 1.3, 2.1) Bialek EyeSmarter Microprocessor VisualCrowding
3	Sept-11	Brief Introduction to V1. Models of Simple and Complex Cells.	Maths Kokkinos	YuilleKersten (Sections 1.3,  2.1)
4	Sept-13	Sparsity  and Natural Images	Maths Sparsity	YuilleKersten (Section 2.2) Barlow
5	Sept-18	Making Decisions I: Statistical Edge Detection and Segmentation	Slides	YuilleKersten (Section 3.1, 3.2)
6	Sept-20	Making Decisions II: Bayes Decision Theory	Slides	YuilleKersten (Section 3.1, 3.2)
7	Sept-25	Hebbian Learning and Regression	HebbRegression Sparsity	YuilleKersten (Section 2.3) Curtis Early Gallant
8	Sept-27	Filters for Binocular Stereo and Motion	Figures Motion	YuilleKersten (Section 2.4)
9	Oct-2	Context and Spatial Interactions Between Neurons I	ContextMarkov	YuilleKersten (Section 4)
10	Oct-4	Context and Spatial Interactions Between Neurons II	ContextMarkov	YuilleKersten (Section 3.3)
11	Oct-9	Context Examples: Weak Membrane, Associative Field	ContextExamples YuilleXuLei	YuilleKersten (Section 4)
12	Oct-11	Introduction to Deep Networks	Slides LowLevelExamples	YuilleKersten (Section 4)
13	Oct-16	Boltzmann Machines & More Context Examples	Boltzmann ContextExamples	YuilleKersten (Section 4)
14	Oct-18	Cue Coupling	BasicCueCoupling CausalCueCombination
15	Oct-23	More Cue Coupling	CausalCueCombination	Primer
16	Oct-25	Deep Networks for Cue Coupling	Slides
17	Oct-30	Perceptrons	Slides	Regression Perceptron
18	Nov-1	What do Deep Networks do?	Yosinski ICLR Stanford
19	Nov-6	Unsupervised Learning	Smirnakis Holistic	PAMI
20	Nov-8	Attention (Bottom-Up)	Niebur Saliency	vonderHeydt EtienneCummings
21	Nov-13	Compositionality (I)	Slides
22	Nov-15	Compositionality (II)	Slides
	Nov-20	Thanksgiving
	Nov-22	Thanksgiving
23	Nov-27	Vision and Language	Slides
24	Nov-29	High Level Vision	ABS Parsing
25	Dec-4	Kalman Filtering	Kalman1 Kalman2	Simulation
26	Dec-6	Review of Course	Slides