Path: utzoo!utgpu!news-server.csri.toronto.edu!rutgers!cs.utexas.edu!uunet!aplcen!haven!adm!lhc!usenet From: usenet@nlm.nih.gov (usenet news poster) Newsgroups: comp.ai.neural-nets Subject: Re: Observations on the State of NN theory Keywords: Genetic Neural Training Pepsi Message-ID: <1990Sep16.030714.15443@nlm.nih.gov> Date: 16 Sep 90 03:07:14 GMT References: <1990Aug3.175023.28210@ariel.unm.edu> <12173@sdcc6.ucsd.edu> <1990Aug6.170953.979@ariel.unm.edu> Reply-To: states@tech.NLM.NIH.GOV (David States) Organization: National Library of Medicine, Bethesda, Md. Lines: 30 In article schraudo@beowulf.ucsd.edu (Nici Schraudolph) writes: >I'd phrase it the other way round: most of the GA/NN research is aimed at >finding a GA (specifically, a genetic representation of NNs) for which >the recombination operator exploits some regularity concerning the basins >of attraction for NN gradient descent. The two main questions are: > >1) Are there any such regularities in the first place, aside from simple > invariances such as flipping the sign of all weights? Sure, suppose you want to train a net to perform multiple discrete tasks such as recgonize English and Spanish speech and you structure the net so that a group of nodes is devoted to each task. In addition, each task specific block of nodes must recognize when its domain is relevant. You then have forced a regularity on the net which gaurantees the existence of a recombindation operator (exchanging task specific nodes enblock). >2) Can we find genetic encodings and/or recombination operators that > exploit them? Yes, but in a sense it is trivial. If you knew the problems were separate, then why make life complicated by combining them in the first place? The existence of task specific groups of neurons in biological networks is obvious (the retina vs visual cortex vs ...). Recombination operators in the training of these nets is less obvious. >Nicol N. Schraudolph, C-014 nici%cs@ucsd.edu David States