It is known that homogeneous networks are ones which perform parallel algorithms, and the dynamics of neural networks are applied to practical problems including combinatorial optimization problems. Both homogeneous and neural networks are parallel networks, and are composed of Boolean elements. Although a large number of studies have been made on the applications of homogeneous threshold networks, little is known about the relation of the dynamics of these networks. In this paper, some results about the dynamics, used to find the lengths of periodic and transient sequences, as built by parallel networks including threshold and homogeneous networks are shown. First, we will show that for non–restricted parallel networks, threshold networks which permit only two elements to transit at each step, and homogeneous networks, it is possible to build periodic and transient sequences of almost any lengths. Further, it will be shown that it is possible for triangular threshold networks to build periodic and transient sequences with short lengths only. As well, homogeneous threshold networks also seem to build periodic and transient sequences with short lengths only. Specifically, we will show a sufficient condition for symmetric homogeneous threshold networks to have periodic sequences with the length 1.

This paper describes some dynamical properties of higher order neural networks with decreasing energy functions. First, we will show that for any symmetric higher order neural network which permits only one element to transit at each step, there are only periodic sequences with the length 1. Further, it will be shown that for any higher order neural network, with decreasing energy functions, which permits all elements to transit at each step, there does not exist any periodic sequence with the length being over k + 1, where k is the order of the network. Lastly, we will give a characterization for higher order neural networks, with the order 2 and a decreasing energy function each, which permit plural elements to transit at each step and have periodic sequences only with the lengh 1.

This paper proposes homogeneous neural networks (HNNs), in which each neuron has identical weights. HNNs can realize shift-invariant associative memory, that is, HNNs can associate not only a memorized pattern but also its shifted ones. The transition property of HNNs is analyzed by the statistical method. We show the probability that each neuron outputs correctly and the error-correcting ability. Further, we show that HNNs cannot memorize over the number,, of patterns, where m is the number of neurons and k is the order of connections.