Title :
Multiplierless digital learning algorithm for cellular neural networks
Author :
Perfetti, Renzo ; Costantini, Giovanni
Author_Institution :
Dept. of Electron. & Inf. Eng., Univ. of Peragia, Italy
fDate :
5/1/2001 12:00:00 AM
Abstract :
A new learning algorithm is proposed for space-varying cellular neural networks, used to implement associative memories. The algorithm exhibits some peculiar features which make it very attractive: the finite precision of connection weights is automatically taken into account as a design constraint; no multiplication is needed for weight computation; learning can be implemented in fixed point digital hardware or simulated on a digital computer without numerical errors
Keywords :
cellular neural nets; content-addressable storage; learning (artificial intelligence); associative memories; connection weights; design constraint; fixed point digital hardware; multiplierless digital learning algorithm; space-varying cellular neural networks; weight computation; Algorithm design and analysis; Associative memory; Cellular neural networks; Computational modeling; Computer errors; Computer simulation; Distributed computing; Error correction; Hardware; Neural networks;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
