Document Type
Conference Item
Publication Date
1-1-2016
Abstract
This paper discusses a complex-valued 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 complex-valued 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.
Keywords
Associative memory, Complex-valued model, Incremental learning
Divisions
fsktm
Event Title
The 23rd International Conference on Neural Information Processing (ICONIP 2016)
Event Location
Kyoto, Japan
Event Dates
17 - 21 October 2016
Event Type
conference