Title :
Pruning via number of links and neuron activities
Author :
Luk, Andrew ; Leung, S.H. ; Lau, W.H. ; Lee, S.L.
Author_Institution :
Dept. of Electron. Eng., City Polytech. of Hong Kong, Kowloon, Hong Kong
Abstract :
A new pruning concept that is based on the number of connections or links and the neuron activities and/or sensitivities is proposed. The concept can be applied to a number of existing algorithms which would then generate a consistent subnetwork even when starting with different initial topologies. The concept can easily be implemented using existing neural network chips by fixing the number of input and output links of each neuron. This new concept is presented and its adaptation on some existing algorithms is outlined. Some of the experimental results are included
Keywords :
convergence; integrated circuit layout; network topology; neural chips; consistent subnetwork; initial topologies; input links; neural network chips; neuron activities; output links; pruning concept; Artificial neural networks; Biological neural networks; Cities and towns; Computer networks; Fault tolerance; Network topology; Neural networks; Neurons; Postal services; Recurrent neural networks;
Conference_Titel :
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-1281-3
DOI :
10.1109/ISCAS.1993.394251
