Skip to main content

More right-solid
More right-solid
More right-solid
SHOW DETAILS
up-solid down-solid
eye
Title
Date Favorited
Creator
Defense Technical Information Archive
by Defense Technical Information Center
texts
eye 16
favorite 1
comment 0
Researchers in Artificial Intelligence have had a difficult time defining the field's goals and assessing its progress. Some have focused on the task of modelling the human brain, others have focused on developing smart machines independent of the constraints of psychological or neurological realism. Over the years the notion of what is an AI task has changed, as problems once thought to be easy have turned out to be hard, and vice versa. This paper discusses some problems that are currently of...
Topics: DTIC Archive, Schank,Roger C, YALE UNIV NEW HAVEN CT DEPT OF COMPUTER SCIENCE, *ARTIFICIAL...
Defense Technical Information Archive
by Defense Technical Information Center
texts
eye 9
favorite 1
comment 0
A major goal of research on networks of neuron-like processing units is to discover efficient learning procedures that allow these networks to construct complex internal representations of their environment. The learning procedures must be capable of modifying the connection strengths in such a way that internal units which are not part of the input or output come to represent important features of the task domain. Several interesting gradient-descent procedures have recently been discovered....
Topics: DTIC Archive, Hinton, Geoffrey E, CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE,...
Defense Technical Information Archive
by Defense Technical Information Center
texts
eye 10
favorite 1
comment 0
This paper analyzes relationships between the roles of descriptions and actions in large scale, open ended, geographically distributed, concurrent systems. Rather than attempt to deal with the complexities and ambiguities of currently implemented descriptive languages, we concentrate our analysis on what can be expressed in the underlying frameworks such as the lambda calculus and first order logic. By this means we conclude that descriptions and actions complement one another; neither being...
Topics: DTIC Archive, Hewitt,Carl, MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB,...
Defense Technical Information Archive
by Defense Technical Information Center
texts
eye 24
favorite 1
comment 0
Learning is defined to be the computation done by a student when there is a transfer of information to him from a teacher. In the particular kind of learning discussed, the teacher names a source and a destination. In the sentence, 'Robbie is like a fox,' fox is the source and Robbie is the destination. The student, on analyzing the teacher's instruction, computes a kind of filter called a transfer frame. It stands between the source and the destination and determines what information is...
Topics: DTIC Archive, Winston,Patrick H, MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB,...
Defense Technical Information Archive
texts
eye 19
favorite 1
comment 0
As advances in computer architecture and changing economics make feasible machines with large-scale parallelism, Artificial Intelligence will require new ways of thinking about computation that can exploit parallelism effectively. We present the actor model of computation as being appropriate for parallel systems, since it organizes knowledge as active objects acting independently, and communicating by message passing. We describe the parallel constructs in our experimental actor interpreter...
Topics: DTIC Archive, Lieberman,Henry, MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB,...
Defense Technical Information Archive
by Defense Technical Information Center
texts
eye 15
favorite 1
comment 0
In this report we describe a distributed control system for a mobile robot which operates in an unmodified office environment occupied by moving people. The robot's controller is composed of over 40 separate processes which run on a loosely connected network of 24 processors. Together this ensemble helps the robot locate empty soda cans, collect them with its arm, and bring them back home. A multi-agent system such as this has many advantages over classic monolithic controllers. For instance,...
Topics: DTIC Archive, Connell, Jonathan H, MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE...
Defense Technical Information Archive
by Defense Technical Information Center
texts
eye 15
favorite 1
comment 0
The initial phases of a program directed toward the realization of complex adaptive logical networks by optical means are described. The logical networks with which the research is concerned are comprised of threshold devices in various configurations. The general hypothesis which underlies the program is that networks of threshold devices can be designed which will be capable of useful application to pattern recognition problems of several types, provided that we can discover simple,...
Topics: DTIC Archive, CAMERON, SCOTT H, IIT RESEARCH INST CHICAGO IL, *MATHEMATICAL LOGIC, *OPTICAL...