Paper available

[Dr. Michael Wong]

The following paper, to be orally presented at NIPS'96, 
is now available via anonymous FTP. (7 pages)
============================================================================
FTP-host: physics.ust.hk
FTP-files: pub/kymwong/rough.ps.gz

    Microscopic Equations in Rough Energy Landscape for Neural Networks

                        K. Y. Michael Wong
                       Department of Physics, 
         The Hong Kong University of Science and Technology,
                 Clear Water Bay, Kowloon, Hong Kong.
                E-mail address: phkywong at usthk.ust.hk


                               ABSTRACT

We consider the microscopic equations for learning problems in neural networks. 
The aligning fields of an example are obtained from the cavity fields, 
which are the fields if that example were absent in the learning process. 
In a rough energy landscape, 
we assume that the density of the metastable states 
obey an exponential distribution, 
yielding macroscopic properties 
agreeing with the first step replica symmetry breaking solution. 
Iterating the microscopic equations provide a learning algorithm, 
which results in a higher stability than conventional algorithms.

============================================================================
FTP instructions:

unix> ftp physics.ust.hk
Name: anonymous
Password: your full email address
ftp> cd pub/kymwong
ftp> get rough.ps.gz
ftp> quit
unix> gunzip rough.ps.gz
unix> lpr rough.ps (or ghostview rough.ps)