Title :
Geometry of neural networks with asymmetric weight matrices
Author :
Kakeya, Hideki ; Okabe, Yoichi
Author_Institution :
Commun. Res. Lab., Minist. of Posts & Telecommun., Koganei, Japan
Abstract :
Dynamics of Hopfield neural networks with asymmetric weights are elucidated from the geometrical viewpoint which is based on the eigenspace analysis of weight matrices. As the examples of asymmetric networks, cross-correlational associative memory and random networks are discussed. Complex dynamical behaviors of asymmetric networks such as spurious memory of cross-correlational associative memory and state transitions of random networks are explained geometrically. Also neuro-window method of asymmetric networks is proposed, which realizes capacity expansion and selective retrieval in cross-correlational associative memory
Keywords :
Hopfield neural nets; content-addressable storage; matrix algebra; Hopfield neural networks; asymmetric networks; asymmetric weight matrices; asymmetric weights; cross-correlational associative memory; eigenspace analysis; neural networks geometry; neuro-window method; random networks; state transitions; Associative memory; Autocorrelation; Control systems; Eigenvalues and eigenfunctions; Geometry; Hopfield neural networks; Neural networks; Neurons; Symmetric matrices;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.814125
