4 search results - page 1 / 1 » Geometric Interpretation of Nonlinear Approximation Capabili... |
ISNN
2004
Springer
14 years 4 months ago
2004
Springer
This paper presents a preliminary study on the nonlinear approximation capability of feedforward neural networks (FNNs) via a geometric approach. Three simplest FNNs with at most f...
NC
1998
14 years 16 days ago
1998
In this paper a new approach for approximation problems involving only few input and output parameters is presented and compared to traditional Backpropagation Neural Networks (BP...
STOC
1993
ACM
14 years 3 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...
ECCC
2000
13 years 11 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 ...