home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!usc!zaphod.mps.ohio-state.edu!darwin.sura.net!jvnc.net!news.edu.tw!news!debbie!dcp77815
- From: dcp77815@csie.nctu.edu.tw (Cheng-Chin Chiang)
- Subject: Kolmogorov's bound on the number of hidden neurons.
- Message-ID: <1992Nov12.141812.9539@debbie.cc.nctu.edu.tw>
- Sender: usenet@debbie.cc.nctu.edu.tw (News Sender)
- Organization: Dep. Computer Science & Engin. of Chiao Tung Univ., Taiwan, ROC
- Date: Thu, 12 Nov 1992 14:18:12 GMT
- Lines: 14
-
-
- Sorry! My last post is incomplete. So, I post it again.
-
- Someone told me that Kolmogorov had proved that a neural network
- needs only 2N+1 hidden neurons to dichotomize an arbitrary training
- set in N-dimensional Euclidean space. Is this true? Can anyone tell
- me where to find the related papers? Any reply is appreciated. If
- it is convenient, please reply it directly to me. Thanks.
-
- Cheng-Chin Chiang
- Dept. of CS & IE
- National Chiao-Tung University
- Hsinchu, Taiwan, ROC
- Email: ccchiang@hsinchu.csie.nctu.edu.tw
-