Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!rutgers!okstate!patil
From: patil@a.cs.okstate.edu (Patil Rajendra Bha)
Newsgroups: comp.ai.neural-nets
Subject: Network initialization
Keywords: random, weights
Message-ID: <5344@okstate.UUCP>
Date: 2 Feb 90 22:22:31 GMT
Organization: Oklahoma State Univ., Stillwater
Lines: 11

Hello,
	Does anybody konw about different methods of initialization of a 
network (different than randomizing the weights) before the training process is
started, also any numerical/ stastical techniques to find different properties 
of datasets, like symmetry(XOR) and other which can help doing prepreocessing on
 the dataset before training in order to reduce the training time.

Thanks,

Rajendra,
OSU(OK).