Statistical Models of Brain and Parallel Computation

Font Size  SML

Lecturer
Kumazawa Itsuo 
Place
Thr7-8(G224)  
Credits
Lecture2  Exercise0  Experiment0
Code
88024
Syllabus updated
2011/9/20
Lecture notes updated
2011/9/20
Semester
Fall Semester

Outline of lecture

閼ウ縺ョ荳ヲ蛻苓ィ育ョ励ョ蜴溽炊繧堤オア險育黄逅蟄ヲ逧縺ォ逅隗」縺励h縺縺ィ縺吶k隧ヲ縺ソ繧帝。梧攝縺ォ縺励↑縺後iシ瑚┻縺ョ諠蝣ア蜃ヲ逅縺ョ莉慕オ縺ソシ御クヲ蛻苓ィ育ョ励r隗」譫舌サ險ュ險医☆繧九◆繧√ョ邨ア險育黄逅蟄ヲ逧譁ケ豕包シ檎「コ邇逧險育ョ励ョ蜴溽炊繧貞ュヲ縺カ縲

Some attempts are introduced to analyze and understand principals behind brain function and massively parallel computation. Methods of statistical physics and probabilistic computation are lectured in addition to programming exercises to confirm the behavior of the parallel systems based on these methods.

Purpose of lecture

This course provides basic knowledge on brain computation, its models for engineering application and statistical theories to understand their behavior. Topics include biological neural networks, artificial neural networks, statistical theories to understand highly parallel computation systems, and programming exercises of parallel computation systems. This course requires basic programming capabilities as theories are learned through computer simulation.

Plan of lecture

01.Introduction of biological neural network (Neurons and Neural Networks).
02.Introduction of statistical mechanics (Magnetic Systems and Spin Glass Models).
03.How to understand the behavior of highly parallel system like a brain. (Analogy between Neural Networks and Spin Glass Models).
04.Models of neurons and computer simulation of their behavior.
05.Deterministic models of recurrent neural networks.
06.Computer simulation of deterministic models of recurrent neural networks.
07.Probabilistic models of recurrent neural networks.
08.Computer simulation of probabilistic models of recurrent neural networks.
09.Theoretical analysis of probabilistic models of recurrent neural networks.
10.Application of a recurrent neural network for solving simultaneous equations.
11.Application of a recurrent neural network for solving combinatorial problems. (Part 1)
12.Application of a recurrent neural network for solving combinatorial problems. (Part 2)

Textbook and reference

Introduction to the Theory of Neural Computation, written by J. Hertz, A. Krogh and R.G. Palmer and published by Westview Press.

Related and/or prerequisite courses

Knowledge on basic computer programming

Evaluation

Assignments on computer simulation

Comments from lecturer

This course would provide practical techniques both on theoretical analysis and programming

Page Top