Design and implementation of neural network logic circuits with global convergence

This paper describes a novel technique to realize high performance digital sequential circuits composed of Hopfield neural networks. For an example of applications of neural networks to logic circuits, a novel gate circuit, full adder circuit and latch circuit using neural networks, which have the global convergence property, are proposed and implemented on breadboard. Here, global convergence means that the energy function is monotonically decreasing and each circuit always operates correctly independently of the initial values. Finally the several digital sequential circuits such as shift register and asynchronous binary counter are designed and verified.