Paper Info
Title
A weighting approach for autoassociative memories to improve accuracy in memorization
Abstract
An autoassociative memory can store multiple information in a neural network, and if some distorted information is presented, the memory can retrieve the most likely information from the network. However, in mathematical models of the autoassociative memory, it is a significant problem that some given information may not be stored correctly in a recurrent artificial neural network (ANN). In this paper, in order to investigate the cause of errors with memorization rules in such a mathematical model, we understand the structure of the energy function for the ANN as a sum of elemental quadratic functions. Then, in order to improve the accuracy in memorization, we propose a weighting approach for the memorization rules so that the structure of the energy function can be altered in a desirable manner. The weights can be determined by solving a theoretically-derived linear program to guarantee perfect memorization of all the given information. Numerical examples demonstrate the effectiveness of the weighting approach.
Year
DOI
Venue
2012
10.1109/IJCNN.2012.6252785
Neural Networks
Keywords
Field
DocType
content-addressable storage,linear programming,recurrent neural nets,ANN,autoassociative memories,elemental quadratic functions,mathematical model,memorization accuracy,memorization rules,neural network,recurrent artificial neural network,theoretically-derived linear program,weighting approach
Autoassociative memory,Weighting,Pattern recognition,Computer science,Quadratic function,Artificial intelligence,Content-addressable storage,Linear programming,Mathematical model,Artificial neural network,Machine learning,Memorization
Conference
ISSN
ISBN
Citations 
2161-4393 E-ISBN : 978-1-4673-1489-3
978-1-4673-1489-3
0
PageRank 
References 
Authors
0.34
1
3
Name
Order
Citations
PageRank
Kazuaki Masuda174.21
Bunpei Fukui200.34
Kenzo Kurihara375.23