TITLE: A Neural Half Cognitive Model of Categorisation
SPEAKER: Chris Huyck (Middlesex University)

ABSTRACT:
This talks centers on paper that Ian Mitchell and I have written
(that's out for review) describin a spiking neural network that learns classes.
Following a classic Psychological task, the model learns some types of
classes better than other types, so the net is a spiking cognitive
model of classification.  A simulated neural system, derived from an
existing model, learns natural kinds, but is unable to form sufficient
attractor states for all of the types of classes.  An extension of the
model, using a combination of singleton and triplets of input
features, learns all of the types.  The models make use of a
principled mechanism for spontaneous firing, and a compensatory
Hebbian learning rule.  Combined, the mechanisms allow learning to
spread to neurons not directly stimulated by the environment.  The
overall network learns the types of classes in a fashion broadly
consistent with the Psychological data.  However, the order of speed
of learning the types is not entirely consistent with the
Psychological data, but may be consistent with one of two
Psychological systems a given person possesses.  A Psychological test
of this hypothesis is proposed.

I'll try to interleave some background, so that those less experienced
with simulated neurons and cognitive models can follow.  The slides from
the talk are on www.cwa.mdx.ac.uk/chris/talks/mdx1116/outline.html