Paper available

[Nicolas Szilas]

Hello,



The following paper is now available by anonymous ftp:

-----------------------------------------------------------------------

		ACTION FOR LEARNING IN NON-SYMBOLIC SYSTEMS
		-------------------------------------------


		Nicolas SZILAS(1) and Eric RONCO(2)

(1) ACROE & LIFIA-IMAG, INPG - 46, av. felix Viallet, 38031 GRENOBLE
Cedex, France
(2) LIFIA-IMAG, INPG - 46, av. felix Viallet, 38031 GRENOBLE
Cedex, France
		


As a cognitive function, learning must be considered as an interactive
process, especially if progressive learning is concerned; the system
must choose every time what to learn and when.

Therefore, we propose an overview of interactive learning algorithms
in the connectionist literature and conclude that most studies are
concerned with the search of the most informative patterns in the
environment, whereas few of them deal with progressive complexity
learning.

Subsequently, some effects of progressive learning are experimently
studied in the framework of supervised learning in layered networks:
the results exhibit great benefits of progressive increasing the
difficulty of the environment.

To design more advanced interactive connectionist learning, we study
the psycholoical automatization theories, which show that taking into
account complex environments implies the emergence of successive
levels of automated processing. Thus, a model is then proposed, based
on hierarchical and incremental integration of modular procesing,
corresponding to a progressive increase of the environment difficulty.

-----------------------------------------------------------------------


To appear in the European Conference on Cognitive Science, Saint-Malo,
France, April 1995.


anonymous ftp to:   imag.fr
filename:           pub/LIFIA/szilas.eccs95.e.ps.Z



----------------------------------------------------------------------
Nicolas SZILAS				e-mail: Nicolas.Szilas at imag.fr
LIFIA-ACROE
46, avenue Felix Viallet		
38031 Grenoble Cedex, France		tel.: (33) 76-57-48-12
----------------------------------------------------------------------