Evolving neural net circuit modules to detect static and dynamic two-dimensional patterns using the CAM Brain Machine (CBM)

This thesis explains the development of neural net modules to detect static and dynamic two-dimensional (2D) patterns using the CAM Brain Machine (CBM).; The CBM is a field programmable gate array-based device. It is a collection of up to 65000 modules. Each of these modules has a neural network, grown in cellular automata cubic space and a genetic algorithm controls the growth of the network. This thesis developed modules that can be used in the visual part of an artificial brain. It is divided into two parts. In the first part, CBM modules to detect static patterns were evolved. In the second part, a CBM module to detect dynamic patterns was evolved. The simulation of the CBM was implemented in the ‘C’ programming language and run on a Windows machine.