Abstract: There are a wide variety of approaches to Artificial Intelligence. Yet interestingly we find that these can all be grouped into four broad categories: Silver Bullets, Core Values, Emergence, and Emulation. We will explain the methodological underpinnings of these categories and give examples of the type of work being pursued in each. Understanding this spectrum of approaches can help defuse arguments between practitioners as well as elucidate common themes.
Paper (PDF), Presentation (PPT)
Abstract: AI has many techniques and tools at its disposal, yet seems to be lacking some special “juice” needed to create a true being. We propose that the missing ingredients are a general theory of motivation and an operational understanding of natural language. The motivation part comes largely from our animal heritage: a real-world agent must continually respond to external events rather than depend on perfect modeling and planning. The language part, on the other hand, is what makes us human: competent participation in a social group requires one-shot learning and the ability to reason about objects and activities that are not present or on-going. In this paper we propose an architecture for self-motivation, and suggest how a language interpreter can be built on top of such a substrate. With the addition of a method for recording and internalizing dialog, we sketch how this can then be used to impart essential cultural knowledge and behaviors.
Paper (PDF), Presentation (PPT)
Last updated: 3/1/08