Visual recognition is essential for most everyday tasks including navigation, reading and socialization. Visual pattern recognition is also important for many engineering applications such as automatic analysis of clinical images, face recognition by computers, security tasks and automatic navigation. In spite of the enormous increase in computational power over the last decade, humans still outperform the most sophisticated engineering algorithms in visual recognition tasks. In this course, we will examine how circuits of neurons in visual cortex represent and transform visual information. The course will cover the following topics: functional architecture of visual cortex, lesion studies, physiological experiments in humans and animals, visual consciousness, computational models of visual object recognition, computer vision algorithms.
Reading assignment discussion: 60 minutes/week
**NOTE: First Class: Monday 09/12/2016. 3:30pm. Biolabs 2062
Location: Biolabs 2062
Topics: Introduction to pattern recognition. Why is vision difficult? Overview of key quesions in the field. Visual Input. Natural image statistics. The retina, LGN and primary visual cortex. Lesion studies in humans and animals. Adventures into terra incognitia: Physiology beyond primary visual cortex. Electrical stimulation in visual cortex and causality - Computational models of visual object recognition. Computer vision and artificial intelligence. Towards understanding subjective visual perception, consciousness and building intelligent machines.
Ullman S (1996) High-level vision. MIT Press.
Wandell BA (1995) Foundations of vision. Sunderland Sinauer Associates.
Chapula LM and Wener JS (editors) (2003). The Visual Neurosciences. MIT Press.
Purves and Lotto. (2003). Why we see what we do. Sinauer Books.
Ripley. Pattern recognition and neural networks (1996). Cambridge University Press.
Rao, Olshausen and Lewicki (eds) (2002). Probabilistic models of the brain. MIT Press.
Koch C (2005) The quest for consciousness. Roberts & Company Publishers.
Regan (2000) Human perception of objects. Sinauer Books.
Dayan and Abbott (2002). Theoretical Neuroscience. MIT Press.
Horn BKP. Robot Vision. MIT Press.
Kriegeskorte N and Kreiman G. (2011) Understanding visual population codes. MIT Press.
Davies ER. (2005). Machine Vision, Third Edition: Theory, Algorithms, Practicalities (Signal Processing and its Applications). Elsevier.
Collaboration Policy Statement
All reading assignments will be discussed in class. During class, collaboration and discussion is not only permitted but actually encouraged. After class, each student must prepare the homework on his/her own. Students should be aware that in this course collaboration of any sort on any work submitted for formal evaluation is not permitted. This means that you may not discuss your problem sets, paper assignments, exams, or any other assignments with other students. All work should be entirely your own. The use of textbooks, books and articles is encouraged. Students must use appropriate citation practices to acknowledge the use of books, articles, websites or lectures, that were consulted to complete your assignments.