Masuyama, N. and Chu, K.L. (2016) An iterative incremental learning algorithm for complexvalued hopfield associative memory. In: The 23rd International Conference on Neural Information Processing (ICONIP 2016), 17  21 October 2016, Kyoto, Japan.

PDF (Full text)
99500051.pdf Download (671kB) 
Abstract
This paper discusses a complexvalued Hopfield associative memory with an iterative incremental learning algorithm. The mathematical proofs derive that the weight matrix is approximated as a weight matrix by the complexvalued pseudo inverse algorithm. Furthermore, the minimum number of iterations for the learning sequence is defined with maintaining the network stability. From the result of simulation experiment in terms of memory capacity and noise tolerance, the proposed model has the superior ability than the model with a complexvalued pseudo inverse learning algorithm.
Item Type:  Conference or Workshop Item (Paper) 

Funders:  UNSPECIFIED 
Uncontrolled Keywords:  Associative memory; Complexvalued model; Incremental learning 
Subjects:  Q Science > QA Mathematics > QA75 Electronic computers. Computer science 
Divisions:  Faculty of Computer Science & Information Technology 
Depositing User:  Mr. Mohd Safri 
Date Deposited:  17 Jan 2017 07:01 
Last Modified:  17 Jan 2017 07:01 
URI:  http://eprints.um.edu.my/id/eprint/16812 
Actions (login required)
View Item 