Joseph A. Lewis

Learn More
In recent years the Artificial Intelligence research group at the University of New Mexico have considered several areas of problem solving in interesting and complex domains. These areas have ranged from the low level explorations of a robot tasked to explore, map, and use a new environment to the development of very sophisticated control algorithms for(More)
We offer a definition of representation based in dynamical systems. Then we present Madcat, a robotic control architecture that uses emergent representation to develop an internal model coupled to the environment through its behavior. The design is inspired by the Copycat program (Mitchell 1993). We present details of the Madcat architecture, the interface(More)
Ambiguity resolution is one of the primary challenges in natural language processing. We present a modified semantic network as a tool for performing ambiguity resolution based on context. The mechanisms used in this architecture resemble neurological processes responsible for the phenomenon of priming in humans. Three sentences, representing unique(More)
—We describe a generalization of Copycat, an important computational architecture for high-level perception. We show how this generalization simplifies the application of computational perception to problems previously beyond the reach of the fluid analogy-making principles underlying Copycat. We also discuss the ways in which this generalization addresses(More)
  • 1