Path: utzoo!attcan!uunet!lll-winken!sol.ctr.columbia.edu!caen!math.lsa.umich.edu!math.lsa.umich.edu!emv From: wstevens@uceng.UC.EDU (william stevenson) Newsgroups: comp.archives Subject: [neural-nets] Re: REFERENCES NEEDED [Neuron Digest V6 #62] Message-ID: <1990Oct26.044310.10982@math.lsa.umich.edu> Date: 26 Oct 90 04:43:10 GMT Sender: emv@math.lsa.umich.edu (Edward Vielmetti) Reply-To: william stevenson Followup-To: comp.ai.neural-nets Organization: (none) Lines: 31 Approved: emv@math.lsa.umich.edu (Edward Vielmetti) X-Original-Newsgroups: comp.ai.neural-nets Archive-name: cascade/20-Oct-90 Original-posting-by: william stevenson Original-subject: Re: REFERENCES NEEDED [Neuron Digest V6 #62] Archive-site: pt.cs.cmu.edu [128.2.254.155] Archive-directory: /afs/cs/project/connect/code Reposted-by: emv@math.lsa.umich.edu (Edward Vielmetti) [edited. --Ed] >I am looking for references on automatic modifcation of structure of a >neural network by learning algorithms(i.e. automatically add some links >and nodes to a neural network or remove them from the neural network. Try Scott Fahlman's Cascade Correlation: adds nodes as needed. Contact him at fahlman@cs.cmu.edu; software (both cascade and quickprop) available by ftp at pt.cs.cmu.edu, in directory /afs/cs/project/connect/code (you must go to this directory directly) I got his reports too, I'm not sure if they're in the same directory. William ;;; For an explanation of this algorithm and some results, see "The ;;; Cascade-Correlation Learning Architecture" by Scott E. Fahlman and ;;; Christian Lebiere in D. S. Touretzky (ed.), "Advances in Neural ;;; Information Processing Systems 2", Morgan Kaufmann, 1990. A somewhat ;;; longer version is available as CMU Computer Science Tech Report ;;; CMU-CS-90-100. ;;;