Title :
Suppression of spurious responses for a class of neural networks with application to telecommunications problems
Author :
Fantacci, R. ; Forti, M. ; Liberatore, A. ; Manetti, S. ; Marini, M.
Author_Institution :
Dept. of Electron. Eng., Florence Univ., Italy
fDate :
30 Apr-3 May 1995
Abstract :
This paper discusses the design of a neural network for solving some classes of combinatorial optimization problems in real time. By means of a suitable design procedure which is not based on energy arguments, it is guaranteed that the network is devoid of spurious responses. An important application is considered to a typical optimization problem arising in the telecommunications field. More specifically, we show how the neural network can be used to take decisions for switching packets and improve switching performance in a fast packet switching fabric with input buffers
Keywords :
Hopfield neural nets; combinatorial mathematics; optimisation; packet switching; telecommunication computing; Hopfield neural networks; combinatorial optimization; fast packet switching fabric; input buffers; real time solution; spurious response suppression; switching packets; switching performance improvement; telecommunications problems; Convergence; Design optimization; Differential equations; Linear matrix inequalities; Neural networks; Neurofeedback; Neurons; Output feedback; Steady-state; Telecommunications;
Conference_Titel :
Circuits and Systems, 1995. ISCAS '95., 1995 IEEE International Symposium on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-2570-2
DOI :
10.1109/ISCAS.1995.519883