By William Eric Leifur Grimson, Ramesh S. Patil

This selection of essays by means of 12 individuals of the MIT employees, offers an inside of document at the scope and expectancies of present examine in a single of the world's significant AI facilities. The chapters on man made intelligence, professional platforms, imaginative and prescient, robotics, and traditional language supply either a vast assessment of present components of job and an evaluate of the sphere at a time of serious public curiosity and fast technological growth. Contents: man made Intelligence (Patrick H. Winston and Karen Prendergast). KnowledgeBased structures (Randall Davis). Expert-System instruments and methods (Peter Szolovits). clinical prognosis: Evolution of structures construction services (Ramesh S. Patil). man made Intelligence and software program Engineering (Charles wealthy and Richard C. Waters). clever average Language Processing (Robert C. Berwick). automated Speech attractiveness and realizing (Victor W. Zue). robotic Programming and synthetic Intelligence (Tomas Lozano-Perez). robotic palms and Tactile Sensing (John M. Hollerbach). clever imaginative and prescient (Michael Brady). Making Robots See (W. Eric L. Grimson). self reliant cellular Robots (Rodney A. Brooks). W. Eric L. Grimson, writer of From photos to Surfaces: A Computational learn of the Human Early imaginative and prescient method (MIT Press 1981), and Ramesh S. Patil are either Assistant Professors within the division of electric Engineering and machine technological know-how at MIT. AI within the Eighties and past is incorporated within the man made Intelligence sequence, edited by way of Patrick H. Winston and Michael Brady.

Show description

Read Online or Download AI in the 1980s and Beyond: An MIT Survey PDF

Best intelligence & semantics books

Computation and reasoning. A type theory for computer science

This booklet develops a kind conception, experiences its houses, and explains its makes use of in desktop technological know-how. The publication focuses specifically on how the research of sort concept could provide a strong and uniform language for programming, software specification and improvement, and logical reasoning. the sort idea constructed the following displays a conceptual contrast among logical propositions and computational facts varieties.

Data Fusion: Concepts and Ideas

This textbook offers a complete creation to the options and suggestion of multisensor information fusion. it truly is an broadly revised moment variation of the author's profitable publication: "Multi-Sensor info Fusion: An creation" which was once initially released through Springer-Verlag in 2007. the most adjustments within the new e-book are: New fabric: except one new bankruptcy there are nearly 30 new sections, 50 new examples and a hundred new references.

Puzzles in Logic, Languages and Computation: The Green Book

"A impressive number of difficulties for somebody who's focused on how human language works!  those books take critical clinical questions and current them in a enjoyable, obtainable way.  Readers workout their logical considering features whereas studying a couple of wide selection of human languages, linguistic phenomena, and computational types.

Extra resources for AI in the 1980s and Beyond: An MIT Survey

Example text

If the task is too narrowly defined, all of the problem solving is done in simply knowing enough to come to this particular source of expertise. There are also substantial difficulties surrounding the problem of in­ exact reasoning, problems recognized in mathematics and psychology some Knowledge-Based Systems 25 Scope How much of the problem is solved in coming to the expert? Getting Religious Some information is not well captured by rules of frames. Simple Representation The standard attribute/object/ value representation is very weak.

Troubleshooting For all those reasons the traditional rule-based technology was found to be insufficient to attack the problem of troubleshooting electronic hardware. Instead we sought to reason from a description of structure and behavior, in the belief that there were fundamental principles that could be captured. Such a system would have a degree of machine independence, would be quickly deployable, given the relevant schematics, and could reason from any set of symptoms, familiar or novel. Knowledge-Based Systems 31 The specific problem of troubleshooting is part of a larger research strategy ( Figure 11).

Such rules can be an effective way to capture expertise in domains where there does not yet exist a more fundamental understanding of cause and effect. , hardware maintenance, deter­ mining what's wrong with my computer when it breaks. A number of difficulties would appear. First, the set of rules would be strongly machine-dependent. The particular set of foibles and symptoms common to one model of computer are often quite different from those of another, meaning the work of accumulating such rules must begin again for each machine.

Download PDF sample

Rated 4.74 of 5 – based on 10 votes