stochastic binary neural networks for qualitatively robust predictive model mapping随机二元神经网络对定性可靠的预测模型映射.pdf

Int. J. Communications, Network and System Sciences, 2012, 5, 603-608 / 10.4236/ijcns.2012.529070 Published Online September 2012 (http://www.SciRP.org/journal/ijcns) Stochastic Binary Neural Networks for Qualitatively Robust Predictive Model Mapping 1 2 A. T. Burrell , P. Papantoni-Kazakos 1Computer Science Department, Oklahoma State University, Stillwater, USA 2Electrical Engineering Department, University of Colorado Denver, Denver, USA Email: tburrell@, Titsa.Papantoni@ Received May 15, 2012; revised June 25, 2012; accepted July 10, 2012 ABSTRACT We consider qualitatively robust predictive mappings of stochastic environmental models, where protection against outlier data is incorporated. We utilize digital representations of the models and deploy stochastic binary neural net- works that are pre-trained to produce such mappings. The pre-training is implemented by a back propagating supervised learning algorithm which converges almost surely to the probabilities induced by the environment, under general er- godicity conditions. Keywords: Qualitative Robustness; Predictive Model Mapping; Stochastic Approximation; Stochastic Binary Neural Networks; Real-Time Supervised Learning; Ergodicity 1. Introduction has been basically limited to techniques arising from the Robbins/Monro [16] method and its extensions, with We consider the case where the statistical behavior of