No abstract

No abstract

Abstruct-This paper presentsThii network provides a more e$cicnt and regular orchitccture compared to ordinary higher-order feedforward networks while maintaining their fast learning property.The ridge polynomial network is a generalization of the pisigma network and uses a special form of ridge polynomials. It provides a natural mechanism for irmmental ntbtwnk growth.Simulation results on a surface fitting problem, the dassiecPtion of high-dimensional data and the realbtion of a mdtlvariate polynomial function are given to highlight the network. In particular, a canstructive 1 developed for the network is shown to yield smooth generalization and steady learning.

This paper introduces a class of higher-order networks called pi-sigma networks (PSNs). PSNs are feedforward networks with a single “hidden” layer of linear summing units and with product units in the output layer. A PSN uses these product units to indirectly incorporate the capabilities of higher-order networks while greatly reducing network complexity. PSNs have only one layer of adjustable weights and exhibit fast learning. A PSN with K summing units provides a constrained Kth order approximation of a continuous function. A generalization of the PSN is presented that can uniformly approximate any continuous function defined on a compact set. The use of linear hidden units makes it possible to mathematically study the convergence properties of various LMS type learning algorithms for PSNs. We show that it is desirable to update only a partial set of weights at a time rather than synchronously updating all the weights. Bounds for learning rates which guarantee convergence are derived. Several simulation results on pattern classification and function approximation problems highlight the capabilities of the PSN. Extensive comparisons are made with other higher order networks and with multilayered perceptrons. The neurobiological plausibility of PSN type networks is also discussed.

Compressive sensing is a sampling method which provides a new approach to efficient signal compression and recovery by exploiting the fact that a sparse signal can be suitably reconstructed from very few measurements. One of the most concerns in compressive sensing is the construction of the sensing matrices. While random sensing matrices have been widely studied, only a few deterministic sensing matrices have been considered. These matrices are highly desirable on structure which allows fast implementation with reduced storage requirements. In this paper, a survey of deterministic sensing matrices for compressive sensing is presented. We introduce a basic problem in compressive sensing and some disadvantage of the random sensing matrices. Some recent results on construction of the deterministic sensing matrices are discussed.

As the long term evolution (LTE) standard comes to an end, 3rd Generation Partnership Project is discussing further evolution of the LTE to meet the international mobile telecommunications advanced requirements, which is referred to as LTE-Advanced (LTE release 10 and beyond). This article first presents the network infrastructure of the LTE-Advanced, and then provides an in-depth overview of enabling technologies from the physical layer aspects, including carrier aggregation, advanced multiple-input multiple-output (MIMO) techniques, wireless relays, enhanced inter-cell interference coordination (eICIC), and coordinated multipoint (CoMP) transmission/reception. In particular, we describe concept and principle of each technology and elaborate important technical details. Moreover, we discuss promising study items of the LTE-Advanced for further enhancement.

No abstract

No abstract