Properties of Feedback Neural Networks

In this paper, we discuss some properties of Block Feedback Neural Networks (B F N). In the first part of the paper, we study network structures. We define formally what a structure is, and then show that the set F n of n-layers B F N structures can be expressed as the direct sum of the set A n of n-layers B F N architectures and the set D n of n-layers B F N dimensions. Both A n and D n are shown to have the structure of a distributive lattice and to indice such structure in F n . Moreover, we show that the computing capabilities of B F N are monotonically non decreasing with the elements of A n ordered according to the lattice structure. In the second part we show that the increasing in the computing power allows the B F N to be universal computers, having the same computing power as a Turing machine. 1 Introduction In this paper, we discuss some properties of the Block Feedback Networks (B F N) model, that we presented in (4). B F Ns are discrete time dynamic multi-layer perceptro..