Preprints available

[Geoffrey Goodhill]

FTP-host: archive.cis.ohio-state.edu
FTP-filename: /pub/neuroprose/goodhill.normalization.ps.Z
FTP-filename: /pub/neuroprose/goodhill.elastic.ps.Z


The following two papers have been accepted for publication in "Neural
Computation": for abstracts and information on obtaining preprints,
see below.

"The Role of Weight Normalization in Competitive Learning"
- Goodhill, G.J. and Barrow, H.G.

"Elastic Net Model of Ocular Dominance: Overall Stripe Pattern and
Monocular Deprivation" - Goodhill, G.J. and Willshaw, D.J.


Geoff Goodhill  (gjg at cns.ed.ac.uk)

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

Instructions for obtaining by anonymous ftp:

% ftp archive.cis.ohio-state.edu (128.146.8.52)
Name: anonymous
ftp> binary
ftp> cd pub/neuroprose
ftp> get goodhill.normalization.ps.Z
ftp> get goodhill.elastic.ps.Z
ftp> quit
% uncompress .....

The papers are of length 11 pages and 6 pages respectively. 

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

        The Role of Weight Normalization in Competitive Learning

                    Goodhill, G.J. and Barrow, H.G.

The effect of different kinds of weight normalization on the outcome
of a simple competitive learning rule is analysed. It is shown that
there are important differences in the representation formed depending
on whether the constraint is enforced by dividing each weight by the
same amount (``divisive enforcement''), or subtracting a fixed amount
from each weight (``subtractive enforcement'').  For the divisive
cases weight vectors spread out over the space so as to evenly
represent ``typical'' inputs, whereas for the subtractive cases the
weight vectors tend to the axes of the space, so as to represent
``extreme'' inputs. The consequences of these differences are examined.


-----

                Elastic Net Model of Ocular Dominance: 
           Overall Stripe Pattern and Monocular Deprivation

                   Goodhill, G.J. and Willshaw, D.J.

The elastic net \cite{durwil87} can account for the development of
both topography and ocular dominance in the mapping from the lateral
geniculate nucleus to primary visual cortex. Here it is further shown
for this model that (a) the overall pattern of stripes produced is
strongly influenced by the shape of the cortex: in particular stripes
with a global order similar to that seen biologically can be produced
under appropriate conditions, and (b) the observed changes in stripe
width associated with monocular deprivation are reproduced in the
model.