Article

Multiplierless digital learning algorithm for cellular neural networks

Dept. of Electron. & Inf. Eng., Univ. of Peragia
IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications 06/2001; DOI:10.1109/81.922467 pp.630 - 635
Source: IEEE Xplore

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

0 0
 · 
0 Bookmarks
 · 
17 Views
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

associative memories
 
connection weights
 
design constraint
 
new
 
numerical errors
 
peculiar features
 
point digital hardware
 

R. Perfetti