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…

In recent years, researchers in artificial intelligence have become interested in replicating human physical reasoning talents in computers. One of the most important skills in this area is predicting how physical systems will behave. This thesis discusses an implemented program…

This paper describes a system for the computer understanding of English. The system answers questions, executes commands, and accepts information in normal English dialog. It uses semantic information and context to understand discourse and to disambiguate sentences. It combines a…

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…

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 Sami people have struggled for centuries to maintain their culture in spite of pressures against it from colonialism. The formal education systems of Norway and Finland have acted in discord with Sami decision-making since their inception. In response to…

La necesidad de curar una enfermedad es
consustancial a la evolución de la especie
humana. En el proceso de desarrollo como
civilización, los mecanismos empleados para conseguir
este fin han ido parejos con el aumento de
conocimientos en diferentes ramas…

Research in decision making has identified the importance of prior knowledge and heuristics on decision making behaviour. These develop with experience in a fashion similar to how domain experts develop specialized knowledge structures and heuristic reasoning patterns. This research is…

This paper presents an algorithm for identifying noun phrase antecedents of third person personal
pronouns, demonstrative pronouns, reflexive pronouns, and omitted pronouns (zero pronouns)
in unrestricted Spanish texts. We define a list of constraints and preferences for different types
of…

The aim of this study is to test the assumption that the depictions of ancient boxing found on Attic Black and Red Figure pottery are accurate. Due to the scarcity of ancient written material and physical evidence, most of our…