Bounds for the computational power and learning complexity of analog neural nets.
It is shown that high-order feedforward neural nets of constant depth with piecewise-polynomial activation functions and arbitrary real weights can be simulated for Boolean inputs and outputs by neural nets of a somewhat larger size and depth with Heaviside gates and weights from {-1,0,1}. This prov...
| Publicado en: | SIAM journal on computing. 26, 3 (1997). |
|---|---|
| Autor Principal: | |
| Formato: | Artigo |
| Idioma: | English |
| Subjects: |