[ Your Name ]  would like to inform you about this article on
Complexity Digest 2005.34 - 12
http://comdig.unam.mx/index.php?id_issue=2005.34#22313
22-Aug-2005

[ Your Message ]



Learning Only When Necessary: Better Memories Of Correlated Patterns In
Networks, Neural Computation
 









Excerpts: Learning in a neuronal network is often thought of as a linear
superposition of synaptic modifications induced by individual stimuli. However,
since biological synapses are naturally bounded, a linear superposition would
cause fast forgetting of previously acquired memories. Here we show that this
forgetting can be avoided by introducing additional constraints on the synaptic
and neural dynamics. We consider Hebbian plasticity of excitatory synapses. A
synapse is modified only if the postsynaptic response does not match the desired
output. With this learning rule, the original memory performances with unbounded
weights are regained, (...).
Source: Learning Only When Necessary: Better Memories Of Correlated Patterns In
Networks With Bounded Synapses[
http://mitpress.mit.edu/catalog/item/default.asp?ttype=6&tid=18799 ], W.
Senn, S. Fusi, Neural Computation, Oct. 2005
Contributed by Atin Das - dasatinyahoo.co.in

You can discuss this article on Articles Forum
http://comdig.unam.mx/topic.php?id_article=22313