IEEE Transactions on Neural Networks · 1999 · 105 citations · 17 references
ComputingComputer ScienceComputational NeuroscienceMachine LearningNeural EngineeringNeural ModelingNeural NetworksSpiking Neural NetworksApproximation PropertiesClamping ConnectionsClamping StrategyFunction Approximation ErrorMultilayer PerceptronNeural Network ModelingRandom Network ModelsSpiking Neural Network Models
This paper examines the function approximation properties of the "random neural-network model" or GNN. The output of the GNN can be computed from the firing probabilities of selected neurons. We consider a feedforward Bipolar GNN (BGNN) model which has both "positive and negative neurons" in the output layer, and prove that the BGNN is a universal function approximator. Specifically, for any f is an element of C([0, 1]s) and any epsilon>0, we show that there exists a feedforward BGNN which approximates f uniformly with error less than epsilon. We also show that after some appropriate clamping operation on its output, the feedforward GNN is also a universal function approximator.
17
Approximation Theory and Methods.
Lars B. Wahlbin, M. J. D. Powell · Mathematics of Computation · 1982 · 825 citations
Wavelet neural networks for function learning
Jun Zhang, G.G. Walter, Yunbo Miao et al. · IEEE Transactions on Signal Processing · 1995 · 719 citations