Multiple layer artificial neural network (ANN) structure is capable of implementing arbitrary input-output mappings. Similarly, hierarchical classifiers, more commonly known as decision trees, possess the capabilities of generating arbitrarily complex decision boundaries in an ndimensional space. Given a decision tree, it is possible to restructure it as a multilayered neural network. The objective of this paper is to show how this mapping of decision trees into multilayer neural network structure can be exploited for the systematic design of a class of layered neural networks, called entropy nets, that have far fewer connections.

This paper presents the analysis and modeling of a spe class of the timetabling problem. The introduced problem is a hybrid one, It combines the school and the university timetabling cases. The set of imposed constraints on the introduced problem is a tight one. This class of problems can be identified in some institutions such as Military Technical College.

The increased processing load experienced in centralized controlled cellular systems of the first and second generation is discussed. The necessity of distributed control is established, and solutions utilizing the concept of distributed control are surveyed. A discussion of a proposed new structure for cellular networks is presented, followed by the appropriate multiple access scheme to be used in such networks.