Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!usc!cs.utexas.edu!helios!mtecv2!barronca
From: barronca@mtecv2.mty.itesm.mx (Ing. Elvia Patricia Barron Cano)
Newsgroups: comp.ai.neural-nets
Subject: Help with network training.
Message-ID: <3388@mtecv2.mty.itesm.mx>
Date: 18 May 91 20:26:46 GMT
Organization: I.T.E.S.M. Campus Monterrey
Lines: 19

Hello!

I have problem with training of the network. I use backpropagation. The network have to learn to classify 529 patterns in 3 categories. The input is binary, there are 36 inputs, but only two are enable.

First, I test whit 50 hidden units, but the total sum of squares was near 10, and to fail in five patterns. I test some times, after with more units (52, 55, 60, 80), and two hidden levels, but the results were aproximate the same. When I made I tested some rate learning and momentums.

I studied the patterns and I made a network with 19 hidden units. I tested with them and 37 units but the response was bad.

Why it can't find the weights?

Please, email me, because i don't read so often this interesting newsgroup.

Thanks, for everything.

Elvia Patricia Barron Cano
barronca@mtecv2.mty.itesm.mx
Centro de Inteligencia Artificial
Instituto Tecnologico de Monterrey
Monterrey, NL, Mexico.