𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Random matrices and neural networks

✍ Scribed by Luca, A. ;Ricciardi, L. M. ;Vasudevan, R.


Publisher
Springer-Verlag
Year
1970
Weight
499 KB
Volume
6
Category
Article
ISSN
0023-5946

No coin nor oath required. For personal study only.


πŸ“œ SIMILAR VOLUMES


Random Approximants and Neural Networks
✍ Y. Makovoz πŸ“‚ Article πŸ“… 1996 πŸ› Elsevier Science 🌐 English βš– 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 =

M-matrices and global convergence of dis
✍ Mauro Forti πŸ“‚ Article πŸ“… 2007 πŸ› John Wiley and Sons 🌐 English βš– 334 KB

## Abstract The paper considers a general class of neural networks possessing discontinuous neuron activations and neuron interconnection matrices belonging to the class of __M__‐matrices or __H__‐matrices. A number of results are established on global __exponential__ convergence of the state and o