TY  - GEN
ID  - cogprints1109
UR  - http://cogprints.org/1109/
A1  - Spratling, Michael
A1  - Hayes, Gillian
Y1  - 2000///
N2  - Nonlinear dendritic processing appears to be a feature of biological neurons and would also be of use in many applications of artificial neural networks. This paper presents a model of an initially standard linear unit which uses unsupervised learning to find clusters of inputs within which inactivity at one synapse can occlude the activity at the other synapses.
TI  - Learning synaptic clusters for non-linear dendritic processing
SP  - 17
AV  - public
EP  - 27
ER  -

<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>