Uniform Approximation Capabilities of Sum-of-Product and Sigma-Pi-Sigma Neural Networks
نویسندگان
چکیده
Investigated in this paper are the uniform approximation capabilities of sum-of-product (SOPNN) and sigma-pi-sigma (SPSNN) neural networks. It is proved that the set of functions that are generated by an SOPNN with its activation function in C(R) is dense in C(K) for any compact K ∈ R , if and only if the activation function is not a polynomial. It is also shown that if the activation function of an SPSNN is in C(R), then the functions generated by the SPSNN are dense in C(K) if and only if the activation function is not a constant.
منابع مشابه
Convergence of Online Gradient Method for Pi-sigma Neural Networks with Inner-penalty Terms
This paper investigates an online gradient method with innerpenalty for a novel feed forward network it is called pi-sigma network. This network utilizes product cells as the output units to indirectly incorporate the capabilities of higherorder networks while using a fewer number of weights and processing units. Penalty term methods have been widely used to improve the generalization performan...
متن کاملLp approximation of Sigma-Pi neural networks
A feedforward Sigma-Pi neural network with a single hidden layer of m neurons is given by mSigma(j=1) cjg (nPi(k=1) xk-thetak(j)/lambdak(j)) where cj, thetak(j), lambdak are elements of R. In this paper, we investigate the approximation of arbitrary functions f: Rn-->R by a Sigma-Pi neural network in the Lp norm. An Lp locally integrable function g(t) can approximate any given function, if and ...
متن کاملEvolutionary Algorithm Training of Higher Order Neural Networks
This chapter aims to further explore the capabilities of the Higher Order Neural Networks class and especially the Pi-Sigma Neural Networks. The performance of Pi-Sigma Networks is evaluated through several well known neural network training benchmarks. In the experiments reported here, Distributed Evolutionary Algorithms are implemented for Pi-Sigma neural networks training. More specifically,...
متن کاملInteger Weight Higher-Order Neural Network Training Using Distributed Differential Evolution
We study the class of Higher-Order Neural Networks and especially the Pi-Sigma Networks. The performance of Pi-Sigma Networks is evaluated through several well known neural network training benchmarks. In the experiments reported here, Distributed Evolutionary Algorithms for Pi-Sigma networks training are presented. More specifically the distributed version of the Differential Evolution algorit...
متن کاملHigher-Order Neural Networks Training Using Differential Evolution
In this contribution, we study the class of Higher-Order Neural Networks, especially Pi-Sigma Networks. The performance of Pi-Sigma Networks is considered through well known neural network training problems. In our experiments, for the training process, we used Evolutionary Algorithms and more specifically the Differential Evolution algorithm. Preliminary results suggest that this training proc...
متن کامل