Paper available

[Cornelius Weber]

The following IJCNN'00 paper is accepted and available on-line.
I will be happy about any feedback.

              Structured models from structured data:
 emergence of modular information processing within one sheet of neurons

Abstract:
In our contribution we investigate how structured information processing
within a neural net can emerge as a result of unsupervised learning from
data. Our model consists of input neurons and hidden neurons
which are recurrently connected
and which represent the thalamus and the cortex, respectively.
On the basis of a maximum likelihood framework the task is
to generate given input data using the code of the hidden units.
Hidden neurons are fully connected allowing for different roles
to play within the unfolding time-dynamics
of this data generation process.
One parameter which is related to the sparsity of neuronal activation
varies across the hidden neurons. As a result of training the net
captures the structure of the data generation process.
Trained on data which are generated by different mechanisms acting in
parallel, the more active neurons will code for the more frequent input
features. Trained on hierarchically generated data, the more active
neurons will code on the higher level where each feature integrates
several lower level features. The results imply that the division of
the cortex into laterally and hierarchically organized areas 
can evolve to a certain degree as an adaptation to the environment.

retreive from:
http://www.cs.tu-berlin.de/~cweber/publications/
(6 pages, 230 KB)