Title :
A novel model of associative memory with biorthogonal properties
Author :
Chen, Ke ; Ting, Yu ; Yan, Pingfan
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
A novel model of associative memory with biorthogonal properties is presented which can be viewed as an improved version of T. Kohonen´s (1977) linear model of associative memory. An iterative algorithm is developed which makes the proposed model directly usable without any limit condition. Several characteristics of the model which are very similar to biological phenomena are discussed. It is shown that the optimal value of an associative memory can always be obtained in the proposed model. Compared with Kohonen´s model, the proposed model has many characteristics closer to the human functions of memory, and can be more conveniently and unconditionally applied in any linear physical system
Keywords :
content-addressable storage; neural nets; Kohonen´s model; associative memory; biorthogonal properties; content addressable storage; iterative algorithm; linear model; neural nets; Artificial intelligence; Associative memory; Computer aided analysis; History; Humans; Linear systems; Neural networks; Physiology; Psychology; Vectors;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170379
