| | |
Summary: In Malaysian Journal of Computer Science, Vol. 10(2), 1997
USING NEURAL NETWORKS TO EXPLICATE HUMAN CATEGORY LEARNING:
A SIMULATION OF CONCEPT LEARNING AND LEXICALISATION
Syed Sibte Raza Abidi
School of Computer Sciences
Universiti Sains Malaysia
11800 Penang
Malaysia
Tel.: 604-6573335
Fax: 604-6573335
email: sraza@cs.usm.my
ABSTRACT
Neural networks, provide a basis for studying various
aspect of human learning and cognitive development in a
seemingly `psychologically plausible' manner. We present
a `hybrid' neural network architecture comprising two
Kohonen maps interrelated by Hebbian connections to
perform a neural network based simulation of the
development of a `concept memory', `word lexicon' and
`concept lexicalisation' in an unsupervised learning
|
