论文信息 - Multiplierless digital learning algorithm for cellular neural networks

Multiplierless digital learning algorithm for cellular neural networks

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.

Giovanni Costantini | Renzo Perfetti

[1] M. Brucoli,et al. A global approach to the design of discrete-time cellular neural networks for associative memories , 1996 .

[2] R. Perfetti,et al. Associative memory design using space-varying cellular neural networks , 1992, CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications.

[3] R. Perfetti. A neural network to design neural networks , 1991 .

[4] Joos Vandewalle,et al. Cellular neural networks as a model of associative memories , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[5] Derong Liu,et al. Sparsely interconnected neural networks for associative memories with applications to cellular neural networks , 1994 .

[6] Lin-Bao Yang,et al. Cellular neural networks: theory , 1988 .

[7] R. Perfetti,et al. Dual-mode space-varying self-designing cellular neural networks for associative memory , 1999 .

[8] Giuseppe Martinelli,et al. Estimating the storage capacity of space-varying cellular neural networks , 1994 .

[9] Péter Szolgay,et al. A fast fixed point learning method to implement associative memory on CNNs , 1997 .

[10] Renzo Perfetti,et al. A synthesis procedure for brain-state-in-a-box neural networks , 1995, IEEE Trans. Neural Networks.

[11] Edgar Sanchez-Sinencio,et al. Nonlinear switched capacitor 'neural' networks for optimization problems , 1990 .