前馈型神经网络容错性研究的现状和展望

杨良土; 胡东成; 罗予频

前馈型神经网络容错性研究的现状和展望

计量
- 文章访问数: 2671
- HTML全文浏览量: 246
- PDF下载量: 716
- 被引次数: 0
出版历程
- 收稿日期: 1997-03-10
- 修回日期: 1998-05-17
- 刊出日期: 1998-11-19

RESEARCHES ON FAULT TOLERANCE OF FEEDFORWARD NEURAL NETWORKS--STATUS AND PROSPECTS

摘要

摘要: 本文首先明确具体地给出了前馈型神经网络(以下简称前馈网络)容错性的基本概念及其研究内容,进而系统地对前馈网络容错性研究的各种分析和设计方法进行了简要的介绍和评述。最后提出了前馈网络容错性有待进一步研究的若干主要问题。
- 前馈型神经网络（前馈网络）; 容错性; 分析; 设计; 综述
Abstract: The concept of fault tolerance of feedforward neural networks and its contents for studying are given clearly and specially. Then, systematically and concisely, various methods for analyzing and increasing the fault tolerance of feedforward neural networks are introduced and evaluated. Finally, some main problems for further researches on the fault tolerance of feedforward neural networks are proposed.

HTML全文

参考文献(1)

Nijhuis, Jos,et al. Limits to the fault-tolerance of a feed forward neural network with learning.Proceedings of the 20th International Symposium on Fault-Tolerant Computing, Chapel Hill, NC, USA: 1990, 228-235.[2]Zhong Zhang, Ruwei Dai. Fault tolerance measure of neural networks. Proceedings of the 3rd Pacific Rim International Conference on Artificial Intelligence, Beijing, China: 1994, I-506-I-511.[3]杨士元,田志宇,童诗白.前向神经网络的故障性能.清华大学学报,1995,35(4): 88-94.[4]Chalapathy Neti, et al. Maximally fault tolerant neural networks. IEEE Trans. on Neural Networks, 1992, NN-3(1): 14-23.[5]徐海银,陈幼平,周祖德,何顶新.容错神经网络及容错BP算法研究.华中理工大学学报,1995, 23(2): 22-26.[6]Kerlirzin P, Refregier P. Theoretical investigation of the robustness of multilayer perceptrons: Analysis of the linear case and extention to nonlinear networks. IEEE Trans. on Neural Networks, 1995, NN-6(3): 560-571.[7]田志宇.与性能相关的可靠性评估方法及ANN可靠性的研究:[博士学位论文].北京:清华大学,1994.[8]Segee B E, Carter M J. Comparative fault tolerance of generalized radial basis function and multilayer perceptron networks. Proceedings of the 1993 IEEE International Conference on Neural Networks, San Francisco, CA, USA: 1993, 1847-1852.[9]Phatak D S, Koren I. Complete and partial fault tolerance of feedforward neural nets. IEEE Trans. on Neural Networks, 1995, NN-6(2): 446-456.[10]Damarla T R, Bhagat P K. Fault Tolerance of Neural Networks. Proceedings of IEEE SOUTHEASTCON-Energy and Information Technology in the Southeast, Columbia, SC, USA: 1989, I-328-I-331.[11]Emmerson M D, et al. Fault tolerance and redundancy of neural nets for the classification of acoustic data. Proceedings of ICASSP 91, Toronto, Ont., Can.: 1991, II-1053-II-1056.[12]Emmerson M D, Damper R I. Determining and improving the fault tolerance of multilayer perceptrons in a pattern-recognition application. IEEE Trans. on Neural Networks, 1993, NN-4(5): 788-793.[13]Pomerleau D A. Reliability estimation for neural network based autonomous driving[J].Robotics and Autonomous Systems.1994, 12(3-4):113-119[14]George B. Fault tolerance and robustness in neural networks. Proceedings of IJCNN, Seattle, WA, USA: 1991, II-986.[15]Chun-shin Lin, Ing-Chyuan Wu. Maximizing fault tolerance in multilayer neural networks. Proceedings of 1994 IEEE International Conference on Neural Networks, Orlando, FL, USA: 1994, I-419-I-424.[16]Sequin C H, Clay R D. Fault tolerance in artificial neural networks. Proceedings of IJCNN, San Diego, CA, USA: 1990, I-703-I-708.[17]Ching-Tai Chiu, et al. Training techniques to obtain fault-tolerant neural networks. Proceedings of the 24th International Symposium on Fault-Tolerant Computing, Austin, TX, USA: 1994, 360-369.[18]Murray A F, Edwards P J. Synaptic weight noise during multilayer perceptron training: Fault tolerance and training improvements. IEEE Trans. on Neural Networks, 1993, NN-4(4): 722-725.[19]Murray A F, Edwards P J. Enhanced M L P. Performance and fault tolerance resulting from synaptic weight noise during training. IEEE Trans. on Neural Networks, 1994, NN-5(5): 792-802.[20]肖本政.前馈网络的性能及学习算法改进的研究:[博士学位论文].北京:清华大学,1992.[21]Minnix Jay I. Fault tolerance of the backpropagation neural network trained on noisy inputs. Proceedings of IJCNN, Baltimore, MD, USA: 1992, III-847-III-852.[22]Minnix Jay I. An analysis of the effects of noisy training sets on the fault tolerance of neural networks. Proceedings of 1991 IEEE International Conference on Systems, Man, and Cybernetics, Charlottesville, VA, USA: 1991, II-713-II-718.[23]Ching-Tai Chiu, et al. Modifying training algorithms for improved fault tolerance. Proceedings of 1994 IEEE International Conference on Neural Networks, Orlando, FL, USA: 1994, I-333-I-338.[24]Phatak D S, Koren I. Fault tolerance of feedforward neural nets for classification tasks. Proceedings of IJCNN, Baltimore, MD, USA: 1992, II-386-II-391.[25]姚增起.用不可靠元件构造可靠系统及其神经网络实现.自动化学报,1990, 16(5): 429-435.[26]魏徽,疏松桂.神经网络控制器的可靠性研究与设计.控制系统可靠性研究--研究成果汇编,北京:中国科学院自动化研究所,1994: 124-129.[27]Ekong D U, et al. Fault tolerant neural networks for control systems. Proceedings of 1993 IEEE WESCANEX, Saskatoon, Ont., Can:1993, 269-275.[28]Yuang-Ming Hsu, et al. Time-redundant multiple computation for fault-tolerant digital neural networks. Proceedlings of ISCAS 95，Seattle, WA, USA: 1995, II-977-II-980.[29]Lon-Chan Chu, Wah B W. Fault tolerant neural networks with hybrid redundancy. Proceedings of IJCNN, San Diego, CA, USA: 1990,11-639-11-649.[30]Jung H Kim, et al. Fault-tolerant artificial neural networks. Proceedings of IJCNN, Seattle, WA, USA: 1991, 11-951.[31]Chung-Hsing Chen, et al. Reconfigurable fault tolerant neural network. Proceedings of IJCNN, Baltimore, MD, USA: 1992, II-547-II-552.[32]Khunasaraphan C, et al. Weight shifting techniques for self-recovery neural networks. IEEE Trans. on Neural Networks, 1994, NN-5(4): 651-658.[33]Khunasaraphan C, et al. Recovering faulty self-organazing neural networks: By weight shifting technique. Proceedings of 1994 IEEE International Conference on Neural Networks, Orlando, FL, USA: 1994, III-1513-III-1518.

施引文献

资源附件(0)

访问统计