The CAM-Brain Machine (CBM): Real Time Evolution andUpdate of a 75 Million Neuron FPGA-Based Artificial Brain

Authors:
Hugo De Garis;Michael Korkin
Affiliations:
Evolutionary Systems Dept., ATR—Human Information Processing Research Laboratories, 2-2 Hikari-dai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan;Genobyte, Inc., 1503 Spruce Street, Suite 3, Boulder CO 80302, USA
Venue:
Journal of VLSI Signal Processing Systems - Special issue on VLSI on custom computing technology
Year:
2000

Citing 8
Cited 2

Cellular automata machines: a new environment for modeling

Cellular automata machines: a new environment for modeling
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Analysis of unconventional evolved electronics

Communications of the ACM
Spikes: exploring the neural code

Spikes: exploring the neural code
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
A ``Spike Interval Information Coding'' Representation for ATR's CAM-Brain Machine (CBM)

ICES '98 Proceedings of the Second International Conference on Evolvable Systems: From Biology to Hardware
CoDi-1Bit: A Simplified Cellular Automata Based Neuron Model

AE '97 Selected Papers from the Third European Conference on Artificial Evolution
ATR's Artificial Brain ("Cam-Brain") Project a Sample of what Individual "CoDi-1Bit" Model Evolved Neural Net Modules can do with Digital and Analog I/O

EH '99 Proceedings of the 1st NASA/DOD workshop on Evolvable Hardware

Initial Evolution Results on CAM-Brain Machines (CBMs)

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
The China-Brain Project: Building China's Artificial Brain Using an Evolved Neural Net Module Approach

Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article introduces ATR's “CAM-Brain Machine”(CBM), an FPGA based piece of hardware which implements a genetic algorithm(GA) to evolve a cellular automata (CA) based neural network circuitmodule, of approximately 1,000 neurons, in about a second, i.e. acomplete run of a GA, with 10,000 s of circuit growths andperformance evaluations. Up to 65,000 of these modules, each of whichis evolved with a humanly specified function, can be downloaded intoa large RAM space, and interconnected according to humanly specifiedartificial brain architectures. This RAM, containing an artificialbrain with up to 75 million neurons, is then updated by the CBM at arate of 130 billion CA cells per second. Such speeds should enablereal time control of robots and hopefully the birth of a new researchfield that we call “brain building”. The first such artificialbrain, to be built by ATR starting in 2000, will be used to controlthe behaviors of a life sized robot kitten called“Robokoneko”.