Subject: will Cascade Correlation work in stochastic mode?
Message-ID: <1993Jan6.182726.29899@cs.brown.edu>
Sender: news@cs.brown.edu
Organization: Brown University Department of Computer Science
Distribution: comp.ai.neural-nets
Date: Wed, 6 Jan 1993 18:27:26 GMT
Lines: 16
Hi
I've been using standard backprop and on-line training, i.e., the algorithm can sample a single randomly generated example at a time. Backprop performs well
when given about 50,000 such examples( thats a small subset of the domain).
However, I would prefer a more robust algorithm. I was looking at Fahlman's
Cascade Correlation. My impression is that Cascor needs epoch training only;
it could be modified to work in stochastic mode, but, in that case, it will
end up creating huge nets with redundant units. Is that correct?
Have people been using Cascade Correlation in stochastic mode? I'll appreciate
