                    A 50,000 Neuron Artificial Brain

50,000 is roughly the number of artificial neurons I can grow/evolve based on cellular automata in the 32 mega CA cell "CAM8" cellular automata machine from MIT that I have on my desk.

Using hand coded cellular automata rules to grow neurons from seeder CA cells, one can then feed in genetic algorithm "chromosome" growth strings into dendrites and axons to grow random neural circuits, whose fitness at controlling some process is measured after the circuit is grown and used to transmit CA based neural signals. Using these ideas and a future "superCAM" our group hopes to build grow/evolve an artificial brain of a billion neurons by 2001. This is quite feasible because RAM is cheap (even gigabytes), the states of the CA cells can be stored in gigabytes of RAM, so too the CA state transition rules. The bottle neck is the CA processor. MIT's CAM8 can update 200 million CA cells of 16 bits per second. Our super CAM should be thousands of times faster.

Reference :

"An Artificial Brain : ATR's CAM-Brain Project Aims to Build/Evolve an Artificial Brain with a Million Neural Net Modules inside a Trillion Cell Cellular Automata Machine", Hugo de Garis, New Generation Computing Journal, Vol. 12, No. 2, Ohmsha & Springer Verlag, 1994.

For more information concerning our CAM-Brain Project, please contact

Dr. Hugo de Garis,
Brain Builder Group,
Evolutionary Systems Dept,
ATR Human Information Processing Research Labs,
2-2 Hikaridai, Seika-cho, Soraku-gun,

Kansai Science City, Kyoto-fu, 619-02, Japan.

tel. + 81 (0)7749 5 1079, fax. + 81 (0)7749 5 1008,
email.  degaris@hip.atr.co.jp