Search

This paper presents the results of an analysis of indicators that can be used to predict whether a student will succeed in a Computer Science Ph.D. program. The analysis was conducted by studying the records of 75 students who have been in the Computer Science Ph.D. program of the University of Alabama in Huntsville. Seventy-seven variables were extracted from each student's record, and the variables were correlated with whether the student did or did not successfully graduate from the program. A multivariate model was developed that predicts success with a high degree of accuracy. Importantly, the model relies on variables that can be determined reasonably early in a student's Ph.D. class work, enabling its use as a selection metric. Hypotheses about the composition of the model are also presented and discussed. [ABSTRACT FROM AUTHOR]

The generalization error bounds found by current error models using the number of effective parameters of a classifier and the number of training samples are usually very loose. These bounds are intended for the entire input space. However, support vector machine (SVM), radial basis function neural network (RBFNN), and multilayer perceptron neural network (MLPNN) are local learning machines for solving problems and treat unseen samples near the training samples to be more important. In this paper, we propose a localized generalization error model which bounds from above the generalization error within a neighborhood of the training samples using stochastic sensitivity measure. It is then used to develop an architecture selection technique for a classifier with maximal coverage of unseen samples by specifying a generalization error threshold. Experiments using 17 University of California at Irvine (UCI) data sets show that, in comparison with cross validation (CV), sequential learning, and two other ad hoc methods, our technique consistently yields the best testing classification accuracy with fewer hidden neurons and less training time. [ABSTRACT FROM AUTHOR]

Details on convention held on June 13-15, 1997 at William and Mary College in Williamsburg, Virginia to survey the different aspects of computers' history. Description about the series of invited papers from historians on computer history; Highlights of the conference.

The Third International Conference on Data Engineering was held in Los Angeles, California on February 2 to 6, 1987. The conference was designed as an international forum for bringing together researchers, developers, managers, strategic planners and other users with an interest in the research, design and development of data engineering methodologies, strategies and systems. Its scope includes computer science, artificial intelligence, electrical engineering, and computer engineering. It featured papers from all major areas of data engineering, including database design and modeling, performance evaluation, algorithms, integrity, security, fault tolerance, query language, artificial intelligence approaches, knowledge bases, database machines, distributed databases and data engineering applications.

Previous analytical work [16], [17] on the resilience of P2P networks has been restricted to disconnection arising from simultaneous failure of all neighbors in routing tables of participating users. In this paper, we focus on a different technique for maintaining consistent graphs—Chord's successor sets and periodic stabilizations—under both static and dynamic node failure. We derive closed-form models for the probability that Chord remains connected under both types of node failure and show the effect of using different stabilization interval lengths (i.e., exponential, uniform, and constant) on the probability of partitioning in Chord. [ABSTRACT FROM AUTHOR]