Sciweavers

Share
ISNN
2007
Springer

A Hierarchical Self-organizing Associative Memory for Machine Learning

10 years 9 months ago
A Hierarchical Self-organizing Associative Memory for Machine Learning
This paper proposes novel hierarchical self-organizing associative memory architecture for machine learning. This memory architecture is characterized with sparse and local interconnections, self-organizing processing elements (PE), and probabilistic synaptic transmission. Each PE in the network dynamically estimates its output value from the observed input data distribution and remembers the statistical correlations between its inputs. Both feed forward and feedback signal propagation is used to transfer signals and make associations. Feed forward processing is used to discover relationships in the input patterns, while feedback processing is used to make associations and predict missing signal values. Classification and image recovery applications are used to demonstrate the effectiveness of the proposed memory for both heteroassociative and auto-associative learning.
Janusz A. Starzyk, Haibo He, Yue Li
Added 08 Jun 2010
Updated 08 Jun 2010
Type Conference
Year 2007
Where ISNN
Authors Janusz A. Starzyk, Haibo He, Yue Li
Comments (0)
books