In this paper we explore the degree to which patents are representative of the magnitude,
direction, and impact of the knowledge spilling out of the university by focusing on MIT, and in particular on the departments of Mechanical and Electrical…

Current approaches to generation for machine translation make use of direct-replacement templates, large grammars, and knowledge-based inferencing techniques. Not only are rules language-specific, but they are too simplistic to handle sentences that exhibit more complex phenomena. Furthermore, these systems are…

This paper describes the connection memory, a machine for concurrently manipulating knowledge stored in semantic networks. We need the connection memory because conventional serial computers cannot move through such networks fast enough. The connection memory sidesteps the problem by providing…

This paper describes some problems and opportunities associated with conceptual modeling for the kind of "open systems" we foresee must and will be increasingly recognized as a central line of computer system development. Computer applications will be based on communication…

We report on a study of how people look for information within email, files, and the Web. When locating a document or searching for a specific answer, people relied on their contextual knowledge of their information target to help them…

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…

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…

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…