An Experimental Study on Nonlinear Function Computation for Neural/Fuzzy Hardware Design
- 2 January 2007
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 18 (1), 266-283
- https://doi.org/10.1109/tnn.2006.884680
Abstract
An experimental study on the influence of the computation of basic nodal nonlinear functions on the performance of (NFSs) is described in this paper. Systems' architecture size, their approximation capability, and the smoothness of provided mappings are used as performance indexes for this comparative paper. Two widely used kernel functions, the sigmoid-logistic function and the Gaussian function, are analyzed by their computation through an accuracy-controllable approximation algorithm designed for hardware implementation. Two artificial neural network (ANN) paradigms are selected for the analysis: backpropagation neural networks (BPNNs) with one hidden layer and radial basis function (RBF) networks. Extensive simulation of simple benchmark approximation problems is used in order to achieve generalizable conclusions. For the performance analysis of fuzzy systems, a functional equivalence theorem is used to extend obtained results to fuzzy inference systems (FISs). Finally, the adaptive neurofuzzy inference system (ANFIS) paradigm is used to observe the behavior of neurofuzzy systems with learning capabilitiesKeywords
This publication has 53 references indexed in Scilit:
- Approximation of sigmoid function and the derivative for hardware implementation of artificial neuronsIEE Proceedings - Circuits, Devices and Systems, 2004
- A comparative study on sufficient conditions for Takagi-Sugeno fuzzy systems as universal approximatorsIEEE Transactions on Fuzzy Systems, 2000
- Circuit design of an adjustable neuron activation function and its derivativeElectronics Letters, 2000
- EditorialComputers and Electrical Engineering, 1999
- General SISO Takagi-Sugeno fuzzy systems with linear rule consequent are universal approximatorsIEEE Transactions on Fuzzy Systems, 1998
- Fuzzy piecewise multilinear and piecewise linear systems as universal approximators in Sobolev normsIEEE Transactions on Fuzzy Systems, 1998
- Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networksIEEE Transactions on Neural Networks, 1995
- Universal Approximation Using Radial-Basis-Function NetworksNeural Computation, 1991
- Layered Neural Networks with Gaussian Hidden Units as Universal ApproximationsNeural Computation, 1990
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989