Generating Communications Systems Through Shared Context
In a distributed model of intelligence, peer components need to communicate with one another. I present a system which enables two agents connected by a thick twisted bundle of wires to bootstrap a simple communication system from observations of a shared environment. The agents learn a large vocabu...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/7079 |
| _version_ | 1826189982562254848 |
|---|---|
| author | Beal, Jacob |
| author_facet | Beal, Jacob |
| author_sort | Beal, Jacob |
| collection | MIT |
| description | In a distributed model of intelligence, peer components need to communicate with one another. I present a system which enables two agents connected by a thick twisted bundle of wires to bootstrap a simple communication system from observations of a shared environment. The agents learn a large vocabulary of symbols, as well as inflections on those symbols which allow thematic role-frames to be transmitted. Language acquisition time is rapid and linear in the number of symbols and inflections. The final communication system is robust and performance degrades gradually in the face of problems. |
| first_indexed | 2024-09-23T08:33:13Z |
| id | mit-1721.1/7079 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:33:13Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/70792019-04-09T18:26:45Z Generating Communications Systems Through Shared Context Beal, Jacob AI distributed amorphous human intelligence genesis robust communication network In a distributed model of intelligence, peer components need to communicate with one another. I present a system which enables two agents connected by a thick twisted bundle of wires to bootstrap a simple communication system from observations of a shared environment. The agents learn a large vocabulary of symbols, as well as inflections on those symbols which allow thematic role-frames to be transmitted. Language acquisition time is rapid and linear in the number of symbols and inflections. The final communication system is robust and performance degrades gradually in the face of problems. 2004-10-20T20:29:08Z 2004-10-20T20:29:08Z 2002-01-01 AITR-2002-002 http://hdl.handle.net/1721.1/7079 en_US AITR-2002-002 58 p. 7876447 bytes 588901 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI distributed amorphous human intelligence genesis robust communication network Beal, Jacob Generating Communications Systems Through Shared Context |
| title | Generating Communications Systems Through Shared Context |
| title_full | Generating Communications Systems Through Shared Context |
| title_fullStr | Generating Communications Systems Through Shared Context |
| title_full_unstemmed | Generating Communications Systems Through Shared Context |
| title_short | Generating Communications Systems Through Shared Context |
| title_sort | generating communications systems through shared context |
| topic | AI distributed amorphous human intelligence genesis robust communication network |
| url | http://hdl.handle.net/1721.1/7079 |
| work_keys_str_mv | AT bealjacob generatingcommunicationssystemsthroughsharedcontext |