by Stephen R. Balzac., Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1987., Title as it appeared in M.I.T. Graduate List, June 1987: An interactive knowledge classifier., Bibliography: leaves 111-112.

This paper presents an adaptive learning model for market-making under the reinforcement learning framework. Reinforcement learning is a learning technique in which agents aim to maximize the long-term accumulated rewards. No knowledge of the market environment, such as the order…

The MIT Artificial Intelligence Project has a variety of goals all bound together by search for principles of intelligent behavior. Among our immediate goals are to develop systems with practical applications for: Visually-controlled automatic manipulation and physical world problem-solving, machine…

We have developed a technique called RISE (Random Image Structure Evolution), by which one may systematically sample continuous paths in a high-dimensional image space. A basic RISE sequence depicts the evolution of an object's image from a random field, along…

The program described here takes as its input a collection of lines, vertices and surfaces describing a scene, and analyzes the scene into a composition of three-dimensional objects. The program does not need to know the form (model, or pattern)…

The human tongue is a versatile, lithe and structurally complex muscular organ that is of paramount importance for many physiological tasks. The lingual musculature is composed of various orthogonally oriented myofiber populations. Furthermore, coupling this knowledge of tissue myoarchitecture with…

Continued advances in the semiconductor industry will require the introduction of new materials and processes concurrent with shrinking device dimensions. These simultaneous demands drastically reduce margins for error and necessitate an increasingly quantitative understanding of semiconductor processes. Leaders of the…

This dissertation investigates how rapid learning occurs in high technology industries, many of which operate in what Bourgeois and Eisenhardt (1988) term "high velocity environments." The dissertation consists of three empirical studies, which follow the method of extended case study…

All intelligence relies on search --- for example, the search for an intelligent agent's next action. Search is only likely to succeed in resource-bounded agents if they have already been biased towards finding the right answer. In artificial agents, the…

Modem society requires reliable and safe operation of its infrastructure. Policymakers believe that, in many industries, competitive markets and regulatory incentives will result in system performance superior to that under command-and-control regulation. Analytical techniques to evaluate the reliability and safety…