DocumentCode :
1892370
Title :
Multi-Sequence Memory with Controllable Steady-State Period
Author :
Xia, Min ; Fang, Jianan ; Tang, Yang
Author_Institution :
Coll. of Inf. Sci. & Technol., Donghua Univ., Shanghai, China
Volume :
1
fYear :
2009
fDate :
10-11 Oct. 2009
Firstpage :
814
Lastpage :
817
Abstract :
Sequential information processing, for instance the sequence memory, plays an important role on many functions of brain. In the workings of the brain, the steady-state period is alterable. But in the existing sequence memory models using hetero-associations, the steady-state period is changeless in the sequence recall. In this paper, multi-sequence memory with controllable steady-state period is proposed. By introducing a novel exponential kernel sampling function and the sampling interval parameter, the steady-state period can be controlled, and the steady-state time steps is equal to the sampling interval parameter. Furthermore, we explained this phenomenon theoretically.
Keywords :
neural nets; exponential kernel sampling function; multisequence memory; sequential information processing; steady-state period; Automatic control; Automation; Biological neural networks; Educational institutions; Information processing; Information science; Kernel; Neurons; Sampling methods; Steady-state; Kernel sampling function; Multi-sequence Memory; Steady-state Period;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on
Conference_Location :
Changsha, Hunan
Print_ISBN :
978-0-7695-3804-4
Type :
conf
DOI :
10.1109/ICICTA.2009.203
Filename :
5287499
Link To Document :
بازگشت