Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!gatech!news.mathworks.com!news.kei.com!simtel!news.sprintlink.net!wizard.pn.com!Germany.EU.net!EU.net!news.eunet.fi!KremlSun!satisfy.kiae.su!carrier.kiev.ua!adamua!news-server
From:  Igor V. Tetko <tetko@bioorganic.kiev.ua>
Subject: NEED: address or a site of PhD of V.Castelli (Stanford) or J.Ratsaby (Pennsylvania)
X-Return-Path: bioorua!bioorganic.kiev.ua!tetko
Reply-To: tetko@bioorganic.kiev.ua
Organization: IBPC
Date: Sat, 30 Sep 1995 12:13:24 GMT
Message-ID: <AAaHJRm8u2@bioorganic.kiev.ua>
Lines: 22
Sender: news-server@adam.kiev.ua

Dear friends,

I was suggested by referees of NIPS*95 conference to refer to PhD
dissertations of V. Castelli (PhD thesis, 1994, Stanford and J. Ratsaby
(PhD thesis, 1994, Univ, Pennsylvania) for using labelled and unlabelled
examples in ANN training. Our work was devoted to measuring complexity in a
data set and then to use this information to select new training data
primarily from regions with high complexity.
Can anybody help me and let me know e-mail / postal addresses of any of these
authors or let me know ftp-site (or WWW), where I can found their works?
Please, send me, if possible, your answer directly to one of my e-mail
addresses:
tetko@bioorganic.kiev.ua
igor@physihp1.unil.ch
bpci@carrier.kiev.ua

Do you know some other works dealing with a resampling technique for ANN
training? measuring data complexity by means of ANNs?

Thank you for your time,

Sincerely Igor V. Tetko
