Function approximation by complex-valued multilayer perceptron with stochastic resonance

This paper explores complex-valued multilayer perceptrons (MLPs) with the mechanism of stochastic resonance (SR). SR is a phenomenon such that a weak periodic signal in the system can be enhanced and detected in the presence of noises. It is expected that the combination of complex-valued encoding and SR mechanism will improve the performance of MLPs, rather than MLPs with either of them. The performances are evaluated through approximations for one- and two-dimensional functions. It is shown that complex-valued MLP with SR could achieve more precise approximations rather than conventional real-valued MLP and complex-valued MLP without SR mechanism.

[1]  Nobuyuki Matsui,et al.  Stochastic resonance neural network and its performance , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[2]  Akira Hirose,et al.  Complex-Valued Neural Networks: Theories and Applications , 2003 .

[3]  Nobuyuki Matsui,et al.  Performance analysis of complex-valued neural networks with stochastic resonance , 2010, Proceedings of SICE Annual Conference 2010.

[4]  Ditto,et al.  Stochastic Resonance in a Neuronal Network from Mammalian Brain. , 1996, Physical review letters.

[5]  Niaoqing Hu,et al.  APPLICATION OF STOCHASTIC RESONANCE THEORY FOR EARLY DETECTING RUB-IMPACT FAULT OF ROTOR SYSTEM , 2001 .

[6]  Kurt Wiesenfeld,et al.  Stochastic resonance and the benefits of noise: from ice ages to crayfish and SQUIDs , 1995, Nature.

[7]  Tohru Nitta,et al.  An Extension of the Back-Propagation Algorithm to Complex Numbers , 1997, Neural Networks.