STUDY ON ATTRACTION DOMAIN AND CONVERGENCE RATE OF HOPFIELD ASSOCIATIVE MEMORY

Hopfield J J Neurons with graded response have collective computational properties like those of ttvo state neurons. Proc. Natl. Acad. Sci. U S. A.1984,81(5): 3088-3092.[2]Michel A N,et a1. Qualitative Analysis of Large-scale Dynamical Systems. New York: Acadimic, 1977, 15, 57.[3]Guez A, et a1 On the stability, storage, capacity, and design of nonlinear continuous neural netnorks. IEEE I2ans. on SMC, 1988, SMC-18(1): 80-87.[4]Michel A N, Fwrel J A Associative memories via artificial neural networks. IEEE Contr[J].Syst. Mag.1990, 10(4):6-17[5]Li J H, Michel A N, Porod W. Qualitative analysis and synthesis of a class of neural networks IEEE Trans. on CAS, 1988; CAS-35(8): 976-986.[6]Michel A N, et a1. Qualitative theory of neural networks. IEEE Trans. on CAS, 1989, CAS-36(2): 229-243.[7]Atiya Met a1. An analog feedback associative memory. IEEE Trans. on NN, 1993, NN-4(1): 117-126.[8]Farrell J A, Michel A N. A synthesis procedure for Hopfields continuous-time associative memory. IEEE Trans. on CAS, 1990, CAS-37(7): 877-884.[9]梁学斌, 吴立德.Hopfield连续联想记忆的吸引域和指数收敛速度的估计及其应用.电子学报,1996,24(1): 40-43.[10]梁学斌,吴立德.连续反馈联想记忆的吸引域和指数收敛速度的估计及其应用.电子科学学刊,1996, 18(1):1-6.[11]曹进德. Hopfield连续联想记忆的吸引域和收敛速度的估计及其应用.信息与控制(已录用).