Cloning cerebellar cortex organization with multi-layer cellular neural network (CNN)

A multilayer cellular neural network (CNN) architecture that takes the cerebellar cortex as a template is described. Massively parallel systems such as cellular automata (CAs) are well suited to implementing any kind of neural network architecture: fully connected or layered, including or not including recursive branches. Using a simple CA accelerator, neural networks from 1000 to 1,000,000 neurons can easily be implemented.<<ETX>>

[1]  J. Henseler,et al.  A cortex-like architecture of a cellular neural network , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[2]  Tosio Kitagawa,et al.  Cell space approaches in biomathematics , 1974 .

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

[4]  S. Y. Kung,et al.  Parallel architectures for artificial neural nets , 1988, IEEE 1988 International Conference on Neural Networks.

[5]  Ryuuzo Shingai,et al.  Maximum Period of 2-Dimensional Uniform Neural Networks , 1979, Inf. Control..

[6]  E. F. Codd,et al.  Cellular automata , 1968 .

[7]  D. Martland.  Dynamic behaviour of Boolean networks , 1989 .

[8]  Tommaso Toffoli,et al.  Cellular automata machines - a new environment for modeling , 1987, MIT Press series in scientific computation.

[9]  D. Slotnick.  The Fastest Computer , 1971 .