Random Approximants and Neural Networks
✍
Y. Makovoz
📂
Article
📅
1996
🏛
Elsevier Science
🌐
English
⚖ 492 KB
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 =