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 circuit module, of approximately 1,000 neurons, in about a second, i.e. a complete run of a GA, with 10,000 s of circuit growths and performance evaluations. Up to 65,000 of these modules, each of which is evolved with a humanly specified function, can be downloaded into a large RAM space, and interconnected according to humanly specified artificial brain architectures. This RAM, containing an artificial brain with up to 75 million neurons, is then updated by the CBM at a rate of 130 billion CA cells per second. Such speeds should enable real time control of robots and hopefully the birth of a new research field that we call “brain building”. The first such artificial brain, to be built by ATR starting in 2000, will be used to control the behaviors of a life sized robot kitten called “Robokoneko”.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
M. Korkin, H. de Garis, F. Gers, and H. Hemmi, “CBM (CAMBrain Machine): A Hardware Tool Which Evolves a Neural Net Module in a Fraction of a Second and Runs a Million Neuron Artificial Brain in Real Time,” Genetic Programming 1997: Proceedings of the Second Annual Conference, J.R. Koza, K. Deb, M. Dorigo, D.B. Fogel, M. Garzon, H. Iba, and R.L. Riolo (Eds.), July 1997.
Xilinx, Inc., The Programmable Logic Data Book 1996, 1996.
D. Rumelhart and J.L. McClelland, Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Cambridge, MA: MIT Press/Bradford Books, 1986.
H. de Garis, “An Artificial Brain: ATR's Cam-Brain Project Aims to Build/Evolve an Artificial BrainWith a Million Neural Net Modules Inside a Trillion Cell Cellular Automata Machine,” New Generation Computing Journal, vol. 12, no.2, 1994.
H. de Garis, F. Gers, M. Korkin, A. Agah, and N. Eiji Nawa, “Building an Artificial Brain Using an FPGA Based ‘CAMBrain Machine',” Artificial Life and Robotics Journal, to appear.
F. Gers, H. de Garis, and M. Korkin, “CoDi-1 Bit: A Simplified Cellular Automata Based Neuron Model,” Proceedings of AE97; Artificial Evolution Conference, Oct. 1997.
D.E. Goldberg, Genetic Algorithms in Search; Optimization; and Machine Learning, Addison-Wesley, 1989.
F. Rieke, D. Warland, R. de Ruyter van Steveninck, and W. Bialek, Spikes: Exploring the Neural Code, Cambridge, MA: MIT Press/Bradford Books, 1997.
M. Korkin, N. Eiji Nawa, and H. de Garis, “A 'spike Interval Information Coding’ Representation for ATR's CAM-Brain Machine (CBM),” Proceedings of the Second International Conference on Evolvable Systems: From Biology to Hardware (ICES'98), Springer-Verlag, Sept. 1998.
E. Sanchez and M. Tomassini, (Eds.), Towards Evolvable Hardware: The Evolutionary Engineering Approach, Springer-Verlag, 1996. Lecture Notes in Computer Science, No. 1062.
T. Higuchi, M. Iwata, and W. Liu (Eds.), Evolvable Systems: From Biology to Hardware, Springer-Verlag, 1997. Lecture Notes in Computer Science, No. 1259.
A. Thompson and P. Layzell, “Analysis of Unconventional Evolved Electronics,” Communications of the ACM, vol. 42, no.4, pp. 71–79, 1999.
An Evolutionary Engineering Consultancy Company based in Boulder, Colorado, at URL http://www.genobyte.com.
H. de Garis, N. Petroff, M. Korkin, and G. Fehr, “Simulation and Evolution of the Motions of a Life Sized Kitten Robot ‘Robokoneko’ to be Controlled by a 32000 Neural Net Module Artificial Brain,” Submitted to publication, available on website http://www.hip.atr.co.jp/~degaris/papers/JCG.html.
T. Toffoli and N. Margolus, Cellular Automata Machines, Cambridge, MA: MIT Press, 1987.
J.G. Eldredge and B.L. Hutchings, “Rrann: The Run-Time Reconfiguration Artificial Neural Network,” Proceedings of the Custom Integrated Circuits Conference, May 1994. Available at http://splish.ee.byu.edu/docs/cicc94.rrann.ps.
MSNBC, “Sit, Aibo, Sit!, MSNBC, Technology Report. Available on website http://www.msnbc.com/news/268649.asp.
H. de Garis, “Genetic Programming: GenNets, Artificial Nervous Systems, Artifical Embryos,” Ph.D. Thesis, Brussels University, Jan. 1992. Available at http://www.hip.atr.co.jp/~degaris.
H. de Garis, A. Buller, M. Korkin, F. Gers, N. Eiji Nawa, and M. Hough, “ATR's Artificial Brain (CAM-Brain) Project: A Sample of What Individual CAM-Brain Modules Can Do With Digital and Analog I/O,” Proceedings of the First NASA/DoD Workshop on Evolvable Hardware, Pasadena, California, July 19–21, 1999, IEEE Computer Society, ISBN 0-7695-0256-3.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
De Garis, H., Korkin, M. The CAM-Brain Machine (CBM): Real Time Evolution and Update of a 75 Million Neuron FPGA-Based Artificial Brain. The Journal of VLSI Signal Processing-Systems for Signal, Image, and Video Technology 24, 241–262 (2000). https://doi.org/10.1023/A:1008149624162
Published:
Issue Date:
DOI: https://doi.org/10.1023/A:1008149624162