DocumentCode :
3351624
Title :
Continuous attractors of a class of recurrent neural networks without lateral inhibition
Author :
Zhang, Haixian ; Zhang, Stones Lei ; Yu, Jiali ; Qu, Hong
Author_Institution :
Sch. of Comput. Sci. & Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu
fYear :
2008
fDate :
21-24 Sept. 2008
Firstpage :
7
Lastpage :
11
Abstract :
Researches on neural population coding have revealed that continuous stimuli, such as orientation, moving direction, and the spatial location of objects could be encoded as continuous attractors in neural networks. The dynamical behaviors of continuous attractors are interesting properties of recurrent neural networks. This paper proposes a class of recurrent neural networks without lateral inhibition. Since there is no general rule to determine the stability of the network without specifying the excitatory connections, individual conditions can be calculated analytically for some particular cases. It shows that the networks can possess continuous attractors if the excitatory connections are in gaussian shape. Simulation examples are employed for illustration.
Keywords :
recurrent neural nets; stability; Gaussian shape; continuous attractors; network stability; neural population coding; recurrent neural networks; Biological neural networks; Brain modeling; Computational intelligence; Computer science; Gaussian processes; Laboratories; Neural networks; Recurrent neural networks; Shape; Stability analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Cybernetics and Intelligent Systems, 2008 IEEE Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-1673-8
Electronic_ISBN :
978-1-4244-1674-5
Type :
conf
DOI :
10.1109/ICCIS.2008.4670891
Filename :
4670891
Link To Document :
بازگشت