Capabilities of a four-layered feedforward neural network: four layers versus three
- 1 March 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 8 (2) , 251-255
- https://doi.org/10.1109/72.557662
Abstract
Neural-network theorems state that only when there are infinitely many hidden units is a four-layered feedforward neural network equivalent to a three-layered feedforward neural network. In actual applications, however, the use of infinitely many hidden units is impractical. Therefore, studies should focus on the capabilities of a neural network with a finite number of hidden units, In this paper, a proof is given showing that a three-layered feedforward network with N-1 hidden units can give any N input-target relations exactly. Based on results of the proof, a four-layered network is constructed and is found to give any N input-target relations with a negligibly small error using only (N/2)+3 hidden units. This shows that a four-layered feedforward network is superior to a three-layered feedforward network in terms of the number of parameters needed for the training data.Keywords
This publication has 8 references indexed in Scilit:
- Backpropagation neural nets with one and two hidden layersIEEE Transactions on Neural Networks, 1993
- A simple method to derive bounds on the size and to train multilayer neural networksIEEE Transactions on Neural Networks, 1991
- Capabilities of a three layer feedforward neural networkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Bounds on the number of hidden neurons in multilayer perceptronsIEEE Transactions on Neural Networks, 1991
- Small Depth Polynomial Size Neural NetworksNeural Computation, 1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989