home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.ai.neural-nets:3357 sci.math:10727 comp.theory:1841
- Path: sparky!uunet!cis.ohio-state.edu!pacific.mps.ohio-state.edu!linac!att!bu.edu!cs!lnd
- From: lnd@cs.bu.edu (Levin)
- Newsgroups: comp.ai.neural-nets,sci.math,comp.theory
- Subject: Re: Kolmogorov's theorem
- Message-ID: <94995@bu.edu>
- Date: 31 Aug 92 14:13:54 GMT
- References: <BtuMKD.14p@acsu.buffalo.edu>
- Sender: news@bu.edu
- Reply-To: Lnd@cs.bu.edu
- Followup-To: comp.ai.neural-nets
- Lines: 12
-
- In article <BtuMKD.14p@acsu.buffalo.edu> ambati@ (Balamural K. Ambati) writes:
- >Could someone post some info. on Kolmogorov's theorem on reconstruction
- >of multidimensional functions and information processing in neural
- >networks? Also refs. if possible. Thanks.
-
- Every continuous multivariate real function can be represented as a depth-4
- composition of continuous one-variate functions and sum. This result of
- Kolmogorov and his student Arnold solves the 13-th Hilbert problem.
-
- A.N.Kolmogorov. Soviet Math. Doklady (DAN SSSR) 108(2), 1956.
- V.I.Arnold. Same 114(4), 1957.
- A.N.Kolmogorov. Same 114(5), 1957.
-