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

摘要

This article introduces the "CAM-Brain Machine" (CBM), an FPGA-based piece of hard- ware that implements a genetic algorithm (GA) to evolve a cellular automata (CA)-based neural network circuit module (of approximately 100 neurons) in seconds (i.e., a complete run of a GA, with 10, 000s of circuit growths and performance evaluations). Up to 65,000 of these modules (each of which is evolved with a specified function) can be down loaded into a gigabyte of RAM space, and interconnected according to specified artificial brain architectures.