Exponential Recurrent Associative Memories: Stability and Relative Capacity

Author

Rajati, Mohammad Reza ; Menhaj, Mohammad Bagher ; Korjani, Mohammad Mehdi ; Dehestani, Alireza

Author_Institution

K.N. Toosi Univ. of Technol., Tehran

fYear

2006

fDate

Nov. 2006

Firstpage

751

Lastpage

755

Abstract

In this paper, relative capacity of a specific higher order Hopfield-type associative memory is considered. This model, which is known as exponential Hopfield neural network is suitable for hardware implementation and is not of a great computational cost. It is shown that, this modification of the Hopfield model significantly improves the storage capacity of the associative memory. We also classify the model via a stability measure, and study the effect of training the network with biased patterns on the stability

Keywords

Hopfield neural nets; asymptotic stability; content-addressable storage; Hopfield neural network; Hopfield-type associative memory; associative memory relative capacity; associative memory stability; exponential recurrent associative memories; Associative memory; Computational efficiency; Hebbian theory; Hopfield neural networks; Mathematical model; Neural network hardware; Neural networks; Neurons; Stability analysis; Telecommunications;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools with Artificial Intelligence, 2006. ICTAI '06. 18th IEEE International Conference on

Conference_Location

Arlington, VA

ISSN

1082-3409

Print_ISBN

0-7695-2728-0

Type

conf

DOI

10.1109/ICTAI.2006.58

Filename

4031969