2026-09-18T22:32:14Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/175102022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Gerald J. Sussman.
Hearn, Robert A. (Robert Aubrey), 1965-
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2005-06-02T15:31:42Z
2005-06-02T15:31:42Z
2001
2001
http://hdl.handle.net/1721.1/17510
49223440
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2001.
Includes bibliographical references (p. 57-58).
Most Artificial Intelligence (AI) work can be characterized as either "high-level" (e.g., logical, symbolic) or "low-level" (e.g., connectionist, behavior-based robotics). Each approach suffers from particular drawbacks. High-level Al uses abstractions that often have no relation to the way real, biological brains work. Low-level Al, on the other hand, tends to lack the powerful abstractions that are needed to express complex structures and relationships. I have tried to combine the best features of both approaches, by building a set of programming abstractions defined in terms of simple, biologically plausible components. At the "ground level", I define a primitive, perceptron-like computational unit. I then show how more abstract computational units may be implemented in terms of the primitive units, and show the utility of the abstract units in sample networks. The new units make it possible to build networks using concepts such as long-term memories, short-term memories, and frames. As a demonstration of these abstractions, I have implemented a simulator for "creatures" controlled by a network of abstract units. The creatures exist in a simple 2D world, and exhibit behaviors such as catching mobile prey and sorting colored blocks into matching boxes. This program demonstrates that it is possible to build systems that can interact effectively with a dynamic physical environment, yet use symbolic representations to control aspects of their behavior.
by Robert A. Hearn.
S.M.
58 p.
3173576 bytes
3173384 bytes
application/pdf
application/pdf
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Building grounded abstractions for artificial intelligence programming
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="fd146457-24e1-4ab2-b828-91d6ee4265c0">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Building grounded abstractions for artificial intelligence programming</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2001</PublicationDate>
<Authors>
<Author>
<DisplayName>Hearn, Robert A. (Robert Aubrey), 1965-</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Most Artificial Intelligence (AI) work can be characterized as either "high-level" (e.g., logical, symbolic) or "low-level" (e.g., connectionist, behavior-based robotics). Each approach suffers from particular drawbacks. High-level Al uses abstractions that often have no relation to the way real, biological brains work. Low-level Al, on the other hand, tends to lack the powerful abstractions that are needed to express complex structures and relationships. I have tried to combine the best features of both approaches, by building a set of programming abstractions defined in terms of simple, biologically plausible components. At the "ground level", I define a primitive, perceptron-like computational unit. I then show how more abstract computational units may be implemented in terms of the primitive units, and show the utility of the abstract units in sample networks. The new units make it possible to build networks using concepts such as long-term memories, short-term memories, and frames. As a demonstration of these abstractions, I have implemented a simulator for "creatures" controlled by a network of abstract units. The creatures exist in a simple 2D world, and exhibit behaviors such as catching mobile prey and sorting colored blocks into matching boxes. This program demonstrates that it is possible to build systems that can interact effectively with a dynamic physical environment, yet use symbolic representations to control aspects of their behavior.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>