Kiyonori Miyasaki

Yukihiro Kamada, Kiyonori Miyasaki

Autonomous threshold element circuit networks are used to investigate the structure of neural networks. With these circuits, as the transition functions are threshold functions, it is necessary to consider the existence of sequences of state configurations that cannot be transitioned. In this study, we focus on all logical functions of four or fewer variables, and we discuss the periodic sequences and transient series that transition from all sequences of state configurations. Furthermore, by using the sequences of state configurations in the Garden of Eden, we show that it is easy to obtain functions that determine the operation of circuit networks.

Yukihiro Kamada, Kiyonori Miyasaki

In this paper, we consider situations in which a given logical function is realized by a multithreshold threshold function. In such situations, constant functions can be easily obtained from multithreshold threshold functions, and therefore, we can show that it becomes possible to optimize a class of high-order neural networks. We begin by proposing a generating method for threshold functions in which we use a vector that determines the boundary between the linearly separable function and the high-order threshold function. By applying this method to high-order threshold functions, we show that functions with the same weight as, but a different threshold than, a threshold function generated by the generation process can be easily obtained. We also show that the order of the entire network can be extended while maintaining the structure of given functions.