Title :
Discrete-time cellular neural networks for associative memories with learning and forgetting capabilities
Author :
Brucoli, Michele ; Carnimeo, Leonarda ; Grassi, Giuseppe
Author_Institution :
Dipartimento di Elettrotecnica ed Elettronica, Politecnico di Bari, Italy
fDate :
7/1/1995 12:00:00 AM
Abstract :
A synthesis procedure for associative memories using Discrete-Time Cellular Neural Networks (DTCNN´s) with learning and forgetting capabilities is presented. The proposed design technique generates networks with the capability of learning new patterns and forgetting old ones without recomputing the whole interconnection matrix and the input vector
Keywords :
cellular neural nets; content-addressable storage; discrete time systems; learning (artificial intelligence); stability; associative memories; discrete-time cellular neural networks; forgetting capabilities; interconnection matrix; learning capabilities; stability analysis; synthesis procedure; Artificial neural networks; Associative memory; Cellular neural networks; Design methodology; Hopfield neural networks; Network synthesis; Neural networks; Sparse matrices; Stability analysis; Very large scale integration;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
