An experiment on evolutionary design of combinational logic circuits using information theory

This paper explores an approach in which information theory is applied to the evolvable hardware field for auto-design and optimization of combinational logic circuits. In our exploratory experiment, two combinational circuits were extrinsically evolved using genetic programming as the evolutionary algorithm and mutual information as the fitness function. In our experiment using MATLAB, we demonstrated that the proposed method could find all-NAND solutions for circuits, which has not been reported in the literature.