Artificial Brains - A Cheap Method for Speeding the Evolution of Neural Network Modules for Artificial Brain Building
Hugo de GARIS, Tang Yu, Di Huang · IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks · 2007
This paper shows how a "Celoxica" electronic accelerator board (containing a Xilinx Virtex II FPGA chip) can be used to speed up, by a factor of about 50 times, the evolution of neural network modules, so that building artificial brains that consist of 10,000 s of interconnected modules can be made practical. We hope that this work will prove to be an important stepping stone towards making the new field of brain building both practical and cheap enough for many research groups to start building their own artificial brains.