On the Chaos Memory Retrieval
In this paper we shall propose a chaos dynamic memory model applied to the chaotic autoassociation memory. The present artificial neuron model is property characterized in terms of a time-dependent sinusoidal activation function to involve a transient chaotic dynamics as well as the energy steepest descent strategy. It is elucidated that the present neural network has a remarkable retrieval ability beyond the conventional models with such a monotonous activation Junction as sigmoidal one. This advantage is found to result from the property of the analogue periodic mapping accompanied with a chaotic behaviour of the neurons as well as the symmetry of the dynamic equation.
cbaos neuron associative memory sinusoidal mapping
MASAHIRO NAKAGAWA
Nagaoka University of Technology,Kamitomioka 1603-1, Nagaoka, Ntigata 940-2188, JAPAN
国际会议
8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)
上海
英文
659-664
2001-11-14（万方平台首次上网日期，不代表论文的发表时间）