This paper describes the structure of, and the ideas behind, a self-applicable specializer of programs, as well as the principles of operation of a compiler generator that has been...
A novel method for projecting points onto a point cloud, possibly with noise, is presented based on the point directed projection (DP) algorithm proposed by Azariadis P., Sapidis ...
Motivated by the slow learning properties of multilayer perceptrons (MLPs) which utilize computationally intensive training algorithms, such as the backpropagation learning algorit...
Abstract. In this paper, we propose a universal network, called recursive dual-net (RDN). It can be used as a candidate of effective interconnection networks for massively parallel...
Given a set of patterns and a similarity measure between them, we will present an optimization framework to approximate a small subset, known as a canonical set, whose members clo...