Title :
A fast fixed point learning method to implement associative memory on CNNs
Author :
Szolgay, Peter ; Szatmári, István ; László, Károly
Author_Institution :
Comput. & Autom. Inst., Hungarian Acad. of Sci., Budapest, Hungary
fDate :
4/1/1997 12:00:00 AM
Abstract :
Cellular Neural Networks (CNNs) with space-varying interconnections are considered here to implement associative memories. A fast learning method is presented to compute the interconnection weights. The algorithm was carefully tested and compared to other methods. Storage capacity, noise immunity, and spurious state avoidance capability of the proposed system are discussed
Keywords :
cellular neural nets; character recognition; content-addressable storage; digital arithmetic; learning (artificial intelligence); Chinese character recognition; algorithm; associative memory; cellular neural networks; fast fixed point learning method; interconnection weights; noise immunity; space-varying interconnections; spurious state avoidance capability; storage capacity; Associative memory; Cellular networks; Cellular neural networks; Cloning; Error correction; Error correction codes; Learning systems; Multidimensional systems; Testing; Turing machines;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
