Please see our class page.
We have added CS 574, CS 564 or instructor consent as a pre-requisite so that this course can focus more on biological vision and use your existing knowledge of computer algorithms.
In many lectures, we will adopt the following approach: [1] describe the major challenges associated with a particular aspect of vision, and analyze those challenges using general mathematical, physics, and signal processing tools; [2] Survey state of the art computer vision and image processing algorithms which give best performance at solving those vision challenges, irrespectively of their biological plausibility; [3] Survey the latest advances in neurobiology (including electrophysiology, psychophysics, fMRI and other experimental techniques, as well as theory and brain modeling) relevant to those vision challenges, and analyze these findings in computational terms; [4] Derive a global view of the problem from a critical comparison between the computer algorithms and neurobiological findings studied.
For issues which have mostly been studied in computational neuroscience, and for which computer vision algorithms are just emerging and highly inspired from neuroscience (e.g., visual attention), the topics above will most likely be approached in the order [1] [3] [2] [4].