Title :
Hopfield model with complementary binary representations
Author :
Jong, T.-L. ; Tai, H.-M.
Author_Institution :
Dept. of Electr. Eng., Texas Tech Univ., Lubbock, TX, USA
fDate :
9/15/1988 12:00:00 AM
Abstract :
A Hopfield neural network model with complementary binary representations is proposed. Advantages of this approach are improvement in memory capacity and error-correction capability, when compared with conventional binary models. Some requirements of the Hopfield model necessary to obtain perfect recall can also be relaxed
Keywords :
content-addressable storage; error correction; neural nets; Hopfield neural network model; complementary binary representations; error-correction capability; memory capacity;
Journal_Title :
Electronics Letters
