一类学习联想神经网络的动态特性研究
STUDIES OF DYNAMIC BEHAVIORS OF A LEARNING ASSOCIATIVE NEURAL NETWORKS
-
摘要: 本文讨论了一类联想神经网络在学习过程中结构变化引起网络平衡点状态变化的动态特性;研究了网络的指数稳定性质;分析了联想过程中输入激励在噪声干扰情况下,网络的滤波能力;得到了一些对于研究联想神经网络学习性质有用的结论。Abstract: The exponential stability and trajectory bounds of the motions of equilibria of an associative neural network under structural variations while learning a new pattern are investigated. The filtering ability of the associative neural network whose input is contaminated by noise is analysed. The obtained results are expected to instruction for further studies of the learning associative neural networks.
-
Hopfield J J. Proc[J].Nat.Acd. Sci. USA.1982, 79:2554-2559[2]Personnaz L, et al J. Statistical Phys., 1986, 43: 411-422.[3]Kosko B. Appl. Opt., 1987 26(23): 4947-4960.[4][4][5]Li J H, et al. IEEE Trans. on CAS, 1988. CAS-35(8): 976-986。Guez A, et al. IEEE Trans.on SMC, 1988. SMC-18( 1): 80-86.[6]Farrell J A, et al. IEEE Trans, on CAS, 1989, CAS-36(22):229-243.[7]Michel A N, et al. IEEE Contl. Syst. Mag: 1990, CSM-10(2):6-17.[8]Zeng Huanglin. J. Electronics. 1992, 9(2):97-104.[9]Yen G, et al. IEEE Trans. on CAS, 1991, CAS-38(10): 1193-1205.[10]Yen G, et al. IEEE Trans. on CAS. 1992. CAS (11)-39 (4): 212-225.[11]Zeng Huanglin. Stability Analysis on Continuous Neural Networks with Slowly Synapse Varying Structure. Proc. IEEE ISCAS. San Diego, Vol, 1, May 1992, 443-448.[12]曾黄麟.四川轻化工学院学报,1993, 6(2): 15-21.
计量
- 文章访问数: 2220
- HTML全文浏览量: 113
- PDF下载量: 446
- 被引次数: 0