Neural Information Processing: Course homepage 2012-2013
This is a course for MSc level students. It runs in semester 2.
The course descriptor can
be found
here.
This course builds on recent insights that in many cases the
computation done by the nervous system can be described using
techniques from system identification theory, probabilistic modelling (machine
learning) and information theory. The aim will be to examine
work on computation in nervous system in terms of these
methods.
The background needed to successfully take this course is a
good grounding in mathematics, particularly with regard to probability
and statistics, vectors and matrices. The mathematical level required
is similar to that which would be obtained by students who did not
have significant difficulties with the courses Mathematics for
Informatics 1-4 taken in the first two years of the Informatics
undergraduate syllabus. The Probabilistic Modelling & Reasoning (PMR)
and Neural Computation (NC) course are recommended as preparation. If in doubt on this
consult the instructor.
Instructors:
Mark van Rossum .
Course Tutor: Paolo Puggioni
Venue
Monday and Thursday 9.00-9.50. 10 BP, rm 2.01
No lectures in the first week. First lecture is Monday 21
Januari.
Course Outline (to be updated)
- Overview of relevant neurobiology
- Neural encoding
- Neural decoding
- Mathematics of Hebbian learning
- Models of early visual coding (sparse coding, ICA and beyond)
- Lateral Interactions and Feedback
- Object recognition
Assessment
There will be two assessed assignments worth in total 25%. There will
be an exam worth 75%.
Out: March 1st, deadline March 11th, 4pm.
The first assignment .
Out: March 15th, deadline March 29th, 4pm.
The second assignment
Books
Theoretical Neuroscience
by P Dayan and L F Abbott (MIT Press 2001) is recommended reading, see also the
list of
errata.
Natural Image Statistics by Aapo Hyvärinen, Jarmo Hurri, and Patrik O. Hoyer.
Full version online.
This will be supplemented by papers from the literature.
Week-by-week listing
No lectures in the first week. First lecture is Monday 21
Januari.
Week 2 (21/1)
Lectures:
Introduction:
lecture slides (2x2) ,
lecture slides (single page)
Neural encoding:
lecture slides (2x2) ,
lecture slides (single page)
Week 2 (28/1)
Lectures:
Neural encoding (cont.)
Week 3 (4/2)
Neural decoding:
lecture slides,
lecture slides (single page)
Week 4 (11/2)
Lectures:
Information theory:
lecture slides,
lecture slides (single page)
Week 5 (18/2)
Innovative teaching week. No lectures.
Week 6 (25/2)
Lectures:
Information theory (cont.).
Week 7 (4/3)
Predicting Retinal Ganglion Cell Receptive Fields,
slides (single page),
slides (4up)
Higher order statistics
slides (single page),
slides (4up)
Web
resource:
Contrast
sensitivity section from Visual Acuity chapter from
Psychophysics of Vision (Michael Kalloniatis and Charles Luu)
at
http://webvision.med.utah.edu/
Background reading on Fourier analysis:
Fourier series,
Fourier
transform
Week 8 (11/3)
No Monday lecture.
Thursday: 2hr lecture by Matthias Hennig.
(This material will not be examined)
slides (single page),
Week 9 (18/3)
Lectures: Higher Order Statistics
slides (single page),
slides (4up),
Lectures: Object recognition
slides (single page),
slides (single page),
Additional material:Beyond ICA (not examined)
slides (single page),
slides (4up)
Week 10 (25/3)
Lectures: Networks
lecture slides (single page),
lecture slides (4up)
This page is maintained by
Chris Williams and Mark van Rossum .