Title :
Recurrent neural network as a KWTA selector: A synthesis procedure
Author :
Costea, Ruxandra L. ; Marinov, Corneliu A.
Author_Institution :
Dept. of Electr. Eng., Polytech. Univ. of Bucharest, Bucharest, Romania
Abstract :
A recurrent continuous time Hopfleld network is rigorously designed to find the K largest elements in a list of currents. Simple formulae link the given parameters (as list separation and the processing time) with computed constants (as gain of amplifiers and interconnection conductance). The results unveil ways of improving circuit performances.
Keywords :
Hopfield neural nets; electric admittance; network synthesis; KWTA selector; amplifier gain; circuit performances; interconnection conductance; recurrent continuous time Hopfleld network; recurrent neural network; synthesis procedure; Artificial neural networks; Integrated circuit interconnections; Neurons; Recurrent neural networks; Sorting; Steady-state; Transient analysis;
Conference_Titel :
Circuits and Systems (ISCAS), 2011 IEEE International Symposium on
Conference_Location :
Rio de Janeiro
Print_ISBN :
978-1-4244-9473-6
Electronic_ISBN :
0271-4302
DOI :
10.1109/ISCAS.2011.5937760
