Functionally equivalent feedforward neural networks

Authors:
Věra Kůrková;Paul C. Kainen
Affiliations:
Institute of Computer Science, P. O. Box 5, 182 07, Prague 8, Czechia;Industrial Math, 3044 N St., N.W., Washington, D.C. 20007 USA
Venue:
Neural Computation
Year:
1994

Citing 7
Cited 3

Wavelets and dilation equations: a brief introduction

SIAM Review
Approximation capabilities of multilayer feedforward networks

Neural Networks
Discrete affine wavelet transforms for analysis and synthesis of feedforward neural networks

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Ten lectures on wavelets

Ten lectures on wavelets
Original Contribution: Uniqueness of the weights for minimal feedforward nets with a given input-output map

Neural Networks
For neural networks, function determines form

Neural Networks
On the geometry of feedforward neural network error surfaces

Neural Computation

How to modify a neural network gradually without changing its input-output functionality

Neural Computation
Neural network tomography: Network replication from output surface geometry

Neural Networks
Feed-forward neural networks and minimal search space learning

CIMMACS'05 Proceedings of the 4th WSEAS international conference on Computational intelligence, man-machine systems and cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

For a feedforward perceptron type architecture with a single hidden layer but with a quite general activation function, we characterize the relation between pairs of weight vectors determining networks with the same input-output function.