Robustness of feedforward neural networks
作者： C.-T. Chiu , K. Mehrotra , C.K. Mohan , S. Ranka
关键词: Artificial neural network 、 Probabilistic neural network 、 Robustness (computer science) 、 Time delay neural network 、 Feed forward 、 Feedforward neural network 、 Control theory 、 Computer science 、 Fault tolerance 、 Artificial intelligence
摘要: Methods are developed for measuring the sensitivity of links and nodes a feedforward neural network, implementing technique to ensure development networks that satisfy well-defined robustness criteria. Experimental observations indicate performance degradation in authors' robust network is significantly less than randomly trained same size by an order magnitude. >
syr.edu参考文章(4)
E.D. Karnin, A simple procedure for pruning back-propagation trained neural networks IEEE Transactions on Neural Networks. ,vol. 1, pp. 239- 242 ,(1990) , 10.1109/72.80236
T. Petsche, B.W. Dickinson, Trellis codes, receptive fields, and fault tolerant, self-repairing neural networks IEEE Transactions on Neural Networks. ,vol. 1, pp. 154- 166 ,(1990) , 10.1109/72.80228
Adam J. Nucci, Franklin J. Rudolph, Michael J. Carter, Operational Fault Tolerance of CMAC Networks neural information processing systems. ,vol. 2, pp. 340- 347 ,(1989)
H. Elsimary, S. Mashally, S. Shahine, Fault tolerance in neural networks international conference on systems engineering. pp. 36- 39 ,(1992) , 10.1109/ICSYSE.1992.236948