[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

unable to replicate bp results with leabra



Hi everyone, I'm doing some simulations involving some
basic time series and I've tried to replicate the
results I've gotten in bp++ with the leabra algorithm.
The problem is, the neurons just seem to freeze on
constant 1 activation and no learning takes place.
I've tried playing around with the K and pct K values
and this doesn't seem to do much. I have one input
layer with feedforward connectivity to a hidden layer
to an output layer with bi-directional connectivity.
it goes like this 10->50->1. Does anyone have some
tips on how to get leabra to work properly? Thanks.

-Aaron

__________________________________________________
Do You Yahoo!?
NEW from Yahoo! GeoCities - quick and easy web site hosting, just $8.95/month.
http://geocities.yahoo.com/ps/info1