SRI International
-
Artificial Intelligence: State Of The Art
The problems tackled by research workers and AI are typically large, complex, and involves ambiguity and uncertainty. AI attempts to come to grips with the real world, with all its confusion and richness, and to interact with people, with all their irrationalities and idiosyncrasies.
-
An Iconic Transform For Sketch Completion and Shape Abstraction
This paper shows how a simple label propagation technique, in conjunction with some novel ideas about how labels can be applied to an image to express semantic knowledge, lead to the simplification of a number of diverse and difficult image analysis tasks.
-
Problem Solving Tactics
This paper describes the basic strategies of automatic problem solving, and then focuses on a variety of tactics for improving their efficiency.
-
Utterance and Objective: Issues In Natural Language Communication
This paper evaluates the capabilities of natural language processing systems against requirements and identifies crucial areas for future research in language processing, common-sense reasoning, and their coordination.
-
Computational Models Of Beliefs and The Semantics Of Belief-Sentences
We present a semantic interpretation for belief sentences and show how this interpretation overcomes some of the difficulties of alternative approaches, especially those based on possible-world semantics.
-
Focusing and Description In Natural Language Dialogues
This paper describes focusing mechanisms based on domain structure clues which have been included in a computer system and, from this perspective, indicates future research problems entailed in modeling the focusing process more generally.
-
Robotic Sensors in Programmable Automation
Characterized by flexibility and the ease of setup for new production tasks, programmable automation employs industrial robots. Today’s robots possess “muscles” only; there is a need to develop intelligent robots that can detect faults and correct errors by using sensors and computer control.
-
Hierarchical Representation Of Three-Dimensional Objects Using Verbal Models
We present a formalism for the computer representation of three-dimensional shapes, that has as its goal to facilitate man-machine communication using verbal, graphic, and visual means. With this method, pieces may be assembled hierarchically using any of several ways of specifying attachment.
-
Map-Guided Interpretation Of Remotely-Sensed Imagery
Geometric correspondence between a sensed image and a symbolic reference map is established in an initial stage of processing by adjusting parameters of a sensor model so that image features predicted from the map optimally match corresponding features extracted from the sensed image.
-
A (14C) Deoxyglucose Study of Somatosensory and Associated Cortical Areas in the Monkey
The strategies used by the macaca monkey brain in controlling the performance of a reaching movement to a visual target have been studied by the quantitative autoradiographic 14C-DG method.
-
A Deductive Approach To Program Synthesis
This approach regards program synthesis as a theorem-proving task and relies on a theorem-proving method that combines the features of transformation rules, unification, and mathematical induction within a single framework.
-

Deafnet
National telecommunications system raises awareness within the deaf community of email’s potential.