The CAM-Brain Machine (CBM): an FPGA-based hardware tool that evolves a 1000 neuron-net circuit module in seconds and updates a 75 million neuron artificial brain for real-time robot control
H. De Garis et M. Korkin, The CAM-Brain Machine (CBM): an FPGA-based hardware tool that evolves a 1000 neuron-net circuit module in seconds and updates a 75 million neuron artificial brain for real-time robot control, NEUROCOMPUT, 42, 2002, pp. 35-68
This article introduces the "CAM-Brain Machine" (CBM), an FPGA-based piece
of hardware that implements a genetic algorithm (GA) to evolve a cellular a
utomata (CA)-based neural network circuit module (of approximately 1000 neu
rons) in seconds (i.e., a complete run of a GA, with 10,000s of circuit gro
wths and performance evaluations). Up to 65,000 of these modules (each of w
hich is evolved with a specified function) can be downloaded into a gigabyt
e of RAM space, and interconnected according to specified artificial brain
architectures. This RAM, containing an "artificial brain" with up to 75 mil
lion 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 hopef
ully the birth of a new research field that we call "brain building". The f
irst such artificial brain (to be built by STARLAB starting in 2001) will b
e used to control the behaviors of a life-sized robot kitten called "Roboki
tty". (C) 2002 Elsevier Science B.V. All rights reserved.