A system for visual recognition is described, with implications for the general problem of representation of knowledge to assist control. The immediate objective is a computer system that will recognize objects in a visual scene, specifically hammers. The computer receives…

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…

Policies to avert the threat of dangerous climate change focus on stabilizing atmospheric carbon dioxide concentrations by drastically reducing anthropogenic emissions of carbon. Such reductions require limiting the use of fossil fuels-which supply the bulk of energy to economic activity,…

The objective of this thesis is to clarify the ways that organizational factors influence nuclear power plant performance in order to improve performance. Therefore, this thesis studied the nuclear power plant organizational environment by identifying and detailing its important work…

As a growing number of firms , especially those in the United States, outsource more of their professional services across geographic and temporal boundaries. Using a multi-faceted framework for this study, this paper shows that very careful analysis is needed…

This thesis considers three complications that arise from applying reinforcement learning to a real-world application. In the process of using reinforcement learning to build an adaptive electronic market-maker, we find the sparsity of data, the partial observability of the domain,…

Humans recognize optical reflectance properties of surfaces such as metal, plastic, or paper from a single image without knowledge of illumination. We develop a machine vision system to perform similar recognition tasks automatically. Reflectance estimation under unknown, arbitrary illumination proves…

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…

One very useful idea in AI research has been the notion of an explicit model of a problem situation. Procedural deduction languages, such as PLANNER, have been valuable tools for building these models. But PLANNER and its relatives are very…

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…