Title :
Capacity expansion of neural networks model using external coding
Author :
Saad, David ; Marom, Emanuel
Author_Institution :
Fac. of Eng., Tel-Aviv Univ., Israel
Abstract :
Summary form only given, as follows. The effects of mapping an ensemble of vectors, using an external coding sequence, on the retrieval efficiency of such an ensemble in a neural network model are studied. Computer simulations show an increase in capacity and in the retrieval efficiency by using such coding. Significant improvements were obtained by using a coded concatenation procedure upon ensembles of highly correlative vectors.<>
Keywords :
encoding; learning systems; memory architecture; neural nets; virtual machines; capacity; coded concatenation procedure; external coding; highly correlative vectors; mapping; neural networks model; retrieval efficiency; vectors; Encoding; Learning systems; Memory architecture; Neural networks; Virtual computers;
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
DOI :
10.1109/IJCNN.1989.118310
