Discussion of the use of Latent Semantic Indexing to determine relevancy in information retrieval focuses on statistical regression and Bayesian methods. Topics include keyword searching; a multiple regression model; how the regression model can aid search methods; and limitations of this approach, including complexity, linearity, and…

This paper summarizes some of the current approaches to student modelling in Intelligent Tutoring Systems (ITS) and proposes ways in which learning algorithms can be applied in ITS. The role of machine learning in tutoring systems is described, including student modelling, teaching strategies, and collaborative learning. The PIXIE system and the…

The learning machine described in this paper acquires concepts representable as conjunctive forms of the predicate calculus and behaviors representable as productions (antecedent-consequent pairs of such conjunctive forms): these concepts and behavior rules are inferred from sequentially presented pairs of examples by an algorithm that is probably…

The training requirements analysis model (TRAMOD) described in this report represents an important portion of the larger effort called the Digital Avionics Information System (DAIS) Life Cycle Cost (LCC) Study. TRAMOD is the second of three models that comprise an LCC impact modeling system for use in the early stages of system development. As…

A study was conducted to investigate learner control of instruction in contrast to response sensitive branching algorithms with respect to two specific types of instructional decisions: (1) whether a student should enter and study a particular instructional module given his score on an associated diagnostic pretest; and (2) when a student should…

Designed initially for use in college computer science courses, the model and computer-aided instructional environment (CAIE) described helps students develop algorithmic problem solving skills. Cognitive skills required are discussed, and implications for developing computer-based design environments in other disciplines are suggested by…

Proposes a problem-oriented, man-machine modelling process which combines algorithms and software to assist decision makers and planners in dealing with complex socio-economic issues. Includes the specific parts in each of the system's three basic elements: a library, special units, and system control units. (Author/DC)

Describes an algorithm that can be used for the construction of an oral presentation. The article suggests how nonnative English-speaking students can be taught to make their presentations more cohesive and to evaluate their cohesiveness with the help of video recordings. (21 references) (Author/CK)

Discusses the results of modeling the performance of searching large text databases via various parallel hardware architectures and search algorithms. The performance under load and the cost of each configuration are compared, and a common search workload used in the modeling is described. (Contains 26 references.) (LRW)

Describes the academic context in which the "French CAT" was created and trialed and gives a detailed consideration of the test presentation platform and operating algorithms. Finally, the article evaluates the first administration of the test and discusses its reliability and validity as a placement instrument for first-year Australian…

Reports algorithm for calculation of term discrimination values that is sufficiently fast in operation to permit use of exact values. Evidence is presented to show that relationship between term discrimination and term frequency is crucially dependent upon type of inter-document similarity measure used for calculation of discrimination values. (13…

To assess whether movement artifacts reported in visual inspection time (IT) tasks were under metacognitive control, 29 young adults in Edinburgh (Scotland) were tested on a dual-task paradigm in which IT was conducted along with a concurrent task. Reports of movement artifacts are not usually examples of metacognitive processing. (SLD)

This report presents a theory of eye movement that accounts for main features of the stochastic behavior of eye-fixation durations and direction of movement of saccades in the process of solving arithmetic exercises of addition and subtraction. The best-fitting distribution of fixation durations with a relatively simple theoretical justification…

The Computerized Decision Training (CDT) system, which focuses on improving and sharpening higher order cognitive skills in judgmental decision making, incorporates an adaptive computer program which learns the student's value structure, and uses this structure to train the student in practical decision making. The application of decision models…

Describes the development of an expert system to help in the selection of materials for academic libraries. A model of selection criteria is explained, computerization of the model is discussed, user-defined criteria are considered, and machine learning of rules through the use of algorithms is described. (18 references) (LRW)