Title :
Enhancing the storage capacity of binary associative memories
Author :
Fellenz, Winfiied A. ; Taylor, John G.
Author_Institution :
Dept. of Math., King´´s Coll., London, UK
Abstract :
We present a simple modification to binary associative memories employing a designated intermediate layer representation which reduces crosstalk between stored patterns and enhances performance and average storage capacity of the network. It is shown that the hidden layer associative network is less dependent on the number of ones in the storage patterns and shows an improved retrieval capacity from incomplete retrieval patterns
Keywords :
content-addressable storage; crosstalk; neural nets; binary associative memory; crosstalk; hidden layer associative network; incomplete retrieval patterns; neural nets; storage capacity; Associative memory; Crosstalk; Decorrelation; Educational institutions; Feedforward systems; Hippocampus; Independent component analysis; Mathematics; Robustness; Vectors;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.831047
