No subject

[Yoshio Takane]

Dear Colleagues,

I am organizing a symposium on "Knowledge integration in neural 
network models" at the International Meeting of the Psychometric Society 
(IMPS-2001) to be held in Osaka, Japan on July 15-19, 2001.  Information 
about the meeting can be found at http://www.ir.rikkyo.ac.jp/imps2001/

I would like to invite anyone interested in presenting a paper on the
topic to submit the title and the abstract (of no more than 300 words)
of the paper to me as soon as possible.  You will be notified of 
acceptance within one week or so of submission.
 
Some prospective speakers so far are:

Shultz, T. R., & Rivest, F.  Knowledge based cascade-correlation network. 
--- This paper presents a method of incorporating prior knowledge learned
previously into a cascade-correlation network learning new but related 
material. 

Asoh, H.  An approximation of nonlinear canonical correlation analysis
using neural network.  --- This paper presents an approximation method 
for nonlinear canonical correlation analysis put forward by Becker &
Hinton (1992).

Takane, Y., & Oshima-Takane, Y.  Nonlinear generalized canonical correlation 
analysis by neural network models.  --- This paper presents nonlinear K-set
canonical correlation analysis as a method for integrating information from 
K concurrent sources.



Yoshio Takane
Professor
McGill University