Title :
Continuous time recurrent neural network designed for KWTA operation
Author :
Costea, Ruxandra L. ; Marinov, Corneliu A.
Author_Institution :
Dept. of Electr. Eng., Polytech. Univ. of Bucharest, Bucharest, Romania
fDate :
July 31 2011-Aug. 5 2011
Abstract :
The paper shows rigorously how to build a KWTA selector from a classical neural Hopfield network in continuous time. The analytical relations between parameters result in a step-by-step accurate and flexible procedure to calculate the amplifiers gain, the processing and the resetting thresholds and the bias current.
Keywords :
Hopfield neural nets; network synthesis; K-winner-take-all network; KWTA selector; classical neural Hopfield network; continuous time recurrent neural network; threshold resetting; Biological neural networks; Electrical engineering; Integrated circuit interconnections; Neurons; Recurrent neural networks; Resistance; Steady-state;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033204
