Evolving an optimal de/convolution function for the neural net modules of ATR´s artificial brain project

This paper reports on efforts to evolve an optimum de/convolution function to be used to convert analog to binary signals (spike trains) and vice versa for the binary input/output signals of the neural net circuit modules evolved at electronic speeds by the so-called “CAM-brain machine“ (CBM) of ATR´s artificial brain project. The CBM is an FPGA based hardware which is used to evolve tens of thousands of cellular automata based neural network circuits or modules at electronic speeds in about a second each, which are then downloaded into artificial brains in a large RAM space. Since state-of-the-art programmable FPGAs constrained us to use 1 bit binary signaling in our neural model, an efficient de/convolution technique is needed to convert digital signals to analog and vice versa. By applying a genetic algorithm to the evolution of the de/convolution function we were able to improve the accurate. Accuracy is important so as to reduce cumulative errors when the output of one neural net module becomes the input of another in long sequential