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

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”.

[1]  Hugo de Garis,et al.  Building an artificial brain using an FPGA based CAM-Brain Machine , 2000, Appl. Math. Comput..

[2]  Hugo de Garis,et al.  CoDi-1Bit: A Simplified Cellular Automata Based Neuron Model , 1997, Artificial Evolution.

[3]  Hugo de Garis,et al.  A "Spike Interval Information Coding" Representation for ATR's CAM-Brain Machine (CBM) , 1998, ICES.

[4]  Tommaso Toffoli,et al.  Cellular automata machines - a new environment for modeling , 1987, MIT Press series in scientific computation.

[5]  William Bialek,et al.  Spikes: Exploring the Neural Code , 1996 .

[6]  Marco Tomassini,et al.  Towards Evolvable Hardware: The Evolutionary Engineering Approach , 1996 .

[7]  Brad Hutchings,et al.  RRANN: the run-time reconfiguration artificial neural network , 1994, Proceedings of IEEE Custom Integrated Circuits Conference - CICC '94.

[8]  Hugo de Garis,et al.  ATR's artificial brain ("CAM-Brain") project: A sample of what individual "CoDi-1 Bit" model evolved neural net modules can do with digital and analog I/O , 1999, Proceedings of the First NASA/DoD Workshop on Evolvable Hardware.

[9]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[10]  J. van Leeuwen,et al.  Evolvable Systems: From Biology to Hardware , 2002, Lecture Notes in Computer Science.

[11]  Eduardo Sanchez.  Field Programmable Gate Array (FPGA) Circuits , 1995, Towards Evolvable Hardware.

[12]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[13]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[14]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[15]  Tommaso Toffoli,et al.  Cellular Automata Machines , 1987, Complex Syst..

[16]  Hugo de Garis,et al.  "CBM (CAM-BRAIN 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 , 1997 .

[17]  G. Kane.  Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .

[18]  Paul J. Layzell,et al.  Analysis of unconventional evolved electronics , 1999, CACM.