Neural networks, approximation theory, and finite precision computation
โ Scribed by Jonathan Wray; Gary G.R. Green
- Publisher
- Elsevier Science
- Year
- 1995
- Tongue
- English
- Weight
- 594 KB
- Volume
- 8
- Category
- Article
- ISSN
- 0893-6080
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
Let D be a set with a probability measure +, +(D)=1, and let K be a compact subset of L q (D, +), where the infimum is taken over all g n of the form g n = n i=1 a i , i , with arbitrary , i # K and a i # R. It is shown that for f # conv(K \_ (&K )), under some mild restrictions, \ n ( f, K ) C q =
Api~rosirnation of' reul fmctiom /I!, f&d~orwcrrd rwtwork.s of' thr ~rsurrl kind is sI~o~'rr to h lxr.scd 011 the fkntlwnet~tml principle of approxitnrrtion hx pip~pwisc-c,orl.sttr,lr fhctiotl.s.
Fluid neural networks can be used as a theoretical framework for a wide range of complex systems as social insects. In this article we show that collective logical gates can be built in such a way that complex computation can be possible by means of the interplay between local interactions and the c