13 search results - page 1 / 3 » Bounds for the computational power and learning complexity o... |
STOC
1993
ACM
13 years 8 months ago
1993
ACM
Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
COLT
1992
Springer
13 years 8 months ago
1992
Springer
This paper deals with finite size networks which consist of interconnections of synchronously evolving processors. Each processor updates its state by applying a "sigmoidal&q...
ISTCS
1993
Springer
13 years 8 months ago
1993
Springer
We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research. Our systems have a xed structure, invariant in time...
ECCC
2000
13 years 4 months ago
2000
This article initiates a rigorous theoretical analysis of the computational power of circuits that employ modules for computing winner-take-all. Computational models that involve ...
GECCO
2007
Springer
13 years 10 months ago
2007
Springer
The brain has long been seen as a powerful analogy from which novel computational techniques could be devised. However, most artificial neural network approaches have ignored the...