Title :
A learning and forgetting algorithm in associative memories: the eigenstructure method
Author :
Yen, Gune ; Michel, Anthony N.
Author_Institution :
Dept. of Electr. Eng., Notre Dame Univ., IN, USA
fDate :
4/1/1992 12:00:00 AM
Abstract :
The authors develop a design technique for associative memories with learning and forgetting capabilities via artificial feedback neural networks. The proposed synthesis technique utilizes the eigenstructure method. Networks generated by this method are capable of learning new patterns as well as forgetting existing patterns without the necessity of recomputing the entire interconnection weights and external inputs. In many respects, the results represent significant improvements over the outer product method, the projection learning rule, and the pseudo-inverse method with stability constraints. Several specific examples are given to illustrate the strengths and weaknesses of the methodology advocated
Keywords :
content-addressable storage; learning systems; neural nets; artificial feedback neural networks; associative memories; design technique; eigenstructure method; forgetting capabilities; learning/forgetting algorithm; pattern learning; synthesis technique; Artificial neural networks; Associative memory; Design methodology; Intelligent networks; Network synthesis; Neural networks; Neurofeedback; Stability;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on