DocumentCode :
1551474
Title :
Analog integrated circuits for the Lotka-Volterra competitive neural networks
Author :
Asai, Tetsuya ; Ohtani, Masashiro ; Yonezu, Hiroo
Author_Institution :
Dept. of Electr. & Electron. Eng., Toyohashi Univ. of Technol., Japan
Volume :
10
Issue :
5
fYear :
1999
fDate :
9/1/1999 12:00:00 AM
Firstpage :
1222
Lastpage :
1231
Abstract :
A subthreshold MOS integrated circuit (IC) is designed and fabricated for implementing a competitive neural network of the Lotka-Volterra (LV) type which is derived from conventional membrane dynamics of neurons and is used for the selection of external inputs. The steady-state solutions to the LV equation can be classified into three types, each of which represents qualitatively different selection behavior. Among the solutions, the winners-share-all (WSA) solution in which a certain number of neurons remain activated in steady states is particularly useful owing to robustness in the selection of inputs from a noisy environment. The measured results of the fabricated LV ICs agree well with the theoretical prediction as long as the influence of device mismatches is small. Furthermore, results of extensive circuit simulations prove that the large-scale LV circuit producing the WSA solution does exhibit a reliable selection compared with winner-take-all circuits, in the possible presence of device mismatches
Keywords :
MOS analogue integrated circuits; circuit simulation; neural nets; Lotka-Volterra competitive neural networks; analog integrated circuits; device mismatches; membrane dynamics; steady-state solutions; subthreshold MOS integrated circuit; winners-share-all solution; Analog integrated circuits; Biomembranes; Circuit noise; Differential equations; MOS integrated circuits; Neural networks; Neurons; Robustness; Steady-state; Working environment noise;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/72.788661
Filename :
788661
Link To Document :
بازگشت