Functionally Equivalent Feedforward Neural Networks
- 1 May 1994
- journal article
- Published by MIT Press in Neural Computation
- Vol. 6 (3) , 543-558
- https://doi.org/10.1162/neco.1994.6.3.543
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.Keywords
This publication has 3 references indexed in Scilit:
- On the Geometry of Feedforward Neural Network Error SurfacesNeural Computation, 1993
- Uniqueness of the weights for minimal feedforward nets with a given input-output mapNeural Networks, 1992
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991