Simplified neural networks algorithm for function approximation on discrete input spaces in high dimension-limited sample applications

Authors:
Syed Shabbir Haider;Xiao-Jun Zeng
Affiliations:
School of Computer Science, University of Manchester, Oxford Road, Manchester M13 9PL, UK;School of Computer Science, University of Manchester, Oxford Road, Manchester M13 9PL, UK
Venue:
Neurocomputing
Year:
2009

Citing 10
Cited 0

Multilayer feedforward networks are universal approximators

Neural Networks
Original Contribution: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

Neural Networks
Neural networks for functional approximation and system identification

Neural Computation
Universal approximation using feedforward neural networks: a survey of some existing methods, and some new results

Neural Networks
Neural netowrk approximation of continuous functionals and continuous functions on compactifications

Neural Networks
Letters: Convex incremental extreme learning machine

Neurocomputing
Approximation Capabilities of Hierarchical Fuzzy Systems

IEEE Transactions on Fuzzy Systems
Neural-network approximation of piecewise continuous functions: application to friction compensation

IEEE Transactions on Neural Networks
Smooth function approximation using neural networks

IEEE Transactions on Neural Networks
Universal approximation using incremental constructive feedforward networks with random hidden nodes

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

Unlike the conventional fully connected feedforward multilayer neural networks for approximating functions on continuous input spaces, this paper investigates simplified neural networks (which use a common linear function in the hidden layer) for approximating functions on discrete input spaces. By developing the corresponding learning algorithms and testing with different data sets, it is shown that, comparing conventional multilayer neural networks for approximating functions on discrete input spaces, the proposed simplified neural network architecture and algorithms can achieve similar or better approximation accuracy especially when dealing with high dimensional-low sample cases, but with a much simpler architecture and less parameters.