Work at SourceForge, help us to make it a better place! We have an immediate need for a Support Technician in our San Francisco or Denver office.

Close

#64 Standalone trainer

open
nobody
5
2004-11-18
2004-11-18
Paolo Marrone
No

When a NN has to be trained in an environment in which
the correct outcome is not known before the next
iteration, it should be possible to store the output of
the network and when the next iteration starts feed
that through the teacher (and change the weights of the
network accordingly) before the network is trained for
another iteration.

Basicly we need the teacher to tell the network how
good or bad the network acted the last iteration, not
the current.

Discussion