Artificial intelligence publications

We examine five greedy hillclimbing procedures that search for attribute sets that generalize well with ID3/C4.5. Experiments suggest hillclimbing in attribute space can yield substantial improvements in generalization performance.

Keywords: Artificial Intelligence, Artificial Intelligence Center, AIC

We show how a special decomposition of general projection matrices, called canonic enables us to build geometric descriptions for a system of cameras which are invariant with respect to a given group…

This paper proposes an algebraic method to generalize the usual equations of structure from motion, when calibration is not available.

Agents situated in dynamic and unpredictable environments require several capabilities, including synthesizing and executing plans while continuing to be responsive to the world.

A new method is proposed for tuning rules by cases, especially in domains in which precise and exceptionless rules are known to be unavailable.

Brutus wanted to kill Caesar. He believed that Caesar was an ordinary mortal, and that, given this, stabbing him was a way of killing him.

For about two thousand years, logic and logicians were stuck on the problem of multiple quantification. Aristotle and his successors had systematized large parts of monadic quantification theory (as we…

The GeoVRML working group of the Web3D Consortium recently announced an extension to the ISO standard Virtual Reality Modeling Language (VRML) to enable just these capabilities.

SRI International developed an information extraction system called FASTUS1 , a permuted acronym standing for "Finite State Automata-based Text Understanding System.

Reasoning systems that are goal-directed and avoid repeatedly solving the same goals can be constructed by formulating the top-down methods metatheoretically for execution by a bottom-up reasoning system (hence, we…