Title :
On the transfer function of macro-neuron
Author :
Emelyanov-Yaroslavsky, L.B. ; Potapov, V.I.
Author_Institution :
Machines & Tools Inst., Moscow, Russia
Abstract :
In artificial intelligence models which are characterized by large volumes of associative memory, it is very important to find a compact description of the memory elements, while preserving the neural logic. The authors describe results of a numerical experiment which shows a way to correctly replace neurons by macro-neurons (ensembles)
Keywords :
content-addressable storage; neural nets; transfer functions; artificial intelligence models; associative memory; ensembles; macro-neurons; memory elements; neural logic; numerical experiment; transfer function; Artificial intelligence; Associative memory; Frequency; Logic; Neural networks; Neurons; Shape; Tail; Transfer functions;
Conference_Titel :
Neuroinformatics and Neurocomputers, 1992., RNNS/IEEE Symposium on
Conference_Location :
Rostov-on-Don
Print_ISBN :
0-7803-0809-3
DOI :
10.1109/RNNS.1992.268626
