Classification ability of single hidden layer feedforward neural networks
- 1 May 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 11 (3) , 799-801
- https://doi.org/10.1109/72.846750
Abstract
Multilayer perceptrons with hard-limiting (signum) activation functions can form complex decision regions. It is well known that a three-layer perceptron (two hidden layers) can form arbitrary disjoint decision regions and a two-layer perceptron (one hidden layer) can form single convex decision regions. This paper further proves that single hidden layer feedforward neural networks (SLFN's) with any continuous bounded nonconstant activation function or any arbitrary bounded (continuous or not continuous) activation function which has unequal limits at infinities (not just perceptrons) can form disjoint decision regions with arbitrary shapes in multidimensional cases. SLFN's with some unbounded activation function can also form disjoint decision regions with arbitrary shapes.Keywords
This publication has 14 references indexed in Scilit:
- General approximation theorem on feedforward networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Comments on "Approximation capability in C(R(n)) by multilayer feedforward networks and related problems".IEEE Transactions on Neural Networks, 1998
- Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functionsIEEE Transactions on Neural Networks, 1998
- Approximation capability in C(R~/sup n/) by multilayer feedforward networks and related problemsIEEE Transactions on Neural Networks, 1995
- Generating-shrinking algorithm for learning arbitrary classificationNeural Networks, 1994
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Bounds on the number of hidden neurons in multilayer perceptronsIEEE Transactions on Neural Networks, 1991
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987