Title :
Cloning cerebellar cortex organization with multi-layer cellular neural network (CNN)
Author_Institution :
Centre Suisse d´´Electron. et de Microtech. SA, Neuchatel, Switzerland
Abstract :
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
Keywords :
cellular automata; feedforward neural nets; cellular automata; cerebellar cortex organization; massively parallel systems; multi-layer cellular neural network; recursive branches; template; Automata; Biological neural networks; Brain modeling; Cellular networks; Cellular neural networks; Cloning; Computer architecture; Humans; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287174