Artificial intelligence publications

A new approach is taken to address the various aspects of the multi-sensor, multi-target tracking (MTT) problem in dense and noisy environments. Instead of fixing the trackers on the potential…

A new approach to characterizing the performance of point-correspondence algorithms is presented. Instead of relying on any "ground truth", it uses the self-consistency of the outputs of an algorithm independently…

Snark, SRI's New Automated Reasoning Kit, is a theorem prover intended for applications in artificial intelligence and software engineering. This document is an example-driven tutorial introduction to snark that will…

A new approach is taken to address the various aspects of the multiple-target tracking (MTT) problem in dense and noisy environments.

MAESTRO is a research and demonstration system developed at SRI International for exploring the contribution of a variety of analysis technologies

This paper demonstrates that extraction accuracy strongly depends on the selection of structure, and presents an algorithm for automatically finding good structures by stochastic optimization.

We describe an algorithm that learns simple, low-coverage wrapper-like extraction patterns, which we then apply to conventional information extraction problems using boosting.

We address: modeling sequential data with HMMs, problems with previous methods: motivation, the maximum entropy Markov model, segmentation of FAQs: experiments and results.

In this paper, we argue that improved usability requires a new representational layer that captures metatheoretic properties of a planning domain.

The goal of this project was to enable knowledge engineers to construct knowledge bases (KBs) faster. To achieve this goal, we investigated two techniques: knowledge reuse and axiom templates. The…