A novel continuous-time neural network for realizing associative memory

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	A novel continuous-time neural network for realizing associative memory
	Tao, Q; Fang, TJ; Qiao, H
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS
	2001-05
卷号	12 期号:2 页码:418-423
摘要	A novel neural network is proposed in this paper for realizing associative memory. The main advantage of the neural network is that each prototype pattern is stored if and only if as an asymptotically stable equilibrium point. Furthermore, the basin of attraction of each desired memory pattern is distributed reasonably (in the Hamming distance sense), and an equilibrium paint that is not asymptotically stable is really the state that cannot be recognized. The proposed network also has a high storage as well as the capability of learning and forgetting, and all its components can be implemented. The network considered is a very simple linear system with a projection on a closed convex set spanned by the prototype patterns. The advanced performance of the proposed network is demonstrated by means of simulation of a numerical example.
关键词	Associative Memory Basin Of Attraction Equilibrium Points Neural Networks Projection Operator
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12580
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
通讯作者	Tao, Q
作者单位	Acad Sinica, Hefei Inst Intelligent Machines
推荐引用方式 GB/T 7714	Tao, Q,Fang, TJ,Qiao, H. A novel continuous-time neural network for realizing associative memory[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS,2001,12(2):418-423.
APA	Tao, Q,Fang, TJ,&Qiao, H.(2001).A novel continuous-time neural network for realizing associative memory.IEEE TRANSACTIONS ON NEURAL NETWORKS,12(2),418-423.
MLA	Tao, Q,et al."A novel continuous-time neural network for realizing associative memory".IEEE TRANSACTIONS ON NEURAL NETWORKS 12.2(2001):418-423.