DocumentCode :
1712660
Title :
“CAM-Brain” ATR´s billion neuron artificial brain project: a three year progress report
Author :
De Garis, Hugo
Author_Institution :
Dept. of Evolutionary Syst., ATR Human Inf. Process. Res. Labs., Kyoto, Japan
fYear :
1996
Firstpage :
886
Lastpage :
891
Abstract :
This paper reports on progress made in the first 3 years of ATR´s CAM-Brain Project, which aims to use evolutionary engineering techniques to build/grow/evolve a RAM-and-cellular-automata based artificial brain consisting of thousands of interconnected neural network modules inside special hardware such as MIT´s Cellular Automata Machine CAM-8, or NTT´s Content Addressable Memory System CAM-System. The states of a billion (later a trillion) 3D cellular automata cells, and millions of cellular automata rules which govern their state changes, can be stored relatively cheaply in giga(tera)bytes of RAM. After 3 years work, the CA rules are almost ready. MIT´s CAM-8 (essentially a serial device) can update 200 million CA cells a second. It is likely that NTT´s CAM-System (essentially a massively parallel device) will be able to update a hundred billion CA cells a second. Hence all the ingredients will soon be ready to create a revolutionary new technology which will allow thousands of evolved neural network modules to be assembled into artificial brains. This in turn will probably create not only a new research field, but hopefully a whole new industry, namely brain building. Building artificial brains with a billion neurons is the aim of ATR´s 8 year CAM-Brain research project, ending in 2001
Keywords :
artificial intelligence; brain; cellular automata; content-addressable storage; genetic algorithms; neural nets; random-access storage; CAM-8; CAM-Brain; Cellular Automata Machine; Content Addressable Memory System; RAM; artificial brain; cellular automata; evolutionary engineering; neural network; research project; Artificial neural networks; Assembly; Biological neural networks; Brain modeling; Cellular neural networks; Detectors; Hardware; Neural networks; Neurons; Read-write memory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation, 1996., Proceedings of IEEE International Conference on
Conference_Location :
Nagoya
Print_ISBN :
0-7803-2902-3
Type :
conf
DOI :
10.1109/ICEC.1996.542720
Filename :
542720
Link To Document :
بازگشت