Computational Introspection
Introspection is the process of thinking about one's own thoughts and feelings. In this paper, I discuss recent attempts to make computational systems that exhibit introspective behavior: [Smith, 982], [Weyhrauch, 1978], and [Doyle, 1980]. Each presents a system capable of manipulating r...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6376 |
| _version_ | 1811097961618210816 |
|---|---|
| author | Batali, John |
| author_facet | Batali, John |
| author_sort | Batali, John |
| collection | MIT |
| description | Introspection is the process of thinking about one's own thoughts and feelings. In this paper, I discuss recent attempts to make computational systems that exhibit introspective behavior: [Smith, 982], [Weyhrauch, 1978], and [Doyle, 1980]. Each presents a system capable of manipulating representations of its own program and current context. I argue that introspective ability is crucial for intelligent systems ??thout it an agent cannot represent certain problems that it must be able to solve. A theory of intelligent action would describe how and why certain actions intelligently achieve an agent's goals. The agent would both embody and represent this theory; it would be implemented as the program for the agent; and the importance of introspection suggests that the agent represent its theory of action to itself. |
| first_indexed | 2024-09-23T17:07:44Z |
| id | mit-1721.1/6376 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T17:07:44Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/63762019-04-12T08:30:26Z Computational Introspection Batali, John Introspection is the process of thinking about one's own thoughts and feelings. In this paper, I discuss recent attempts to make computational systems that exhibit introspective behavior: [Smith, 982], [Weyhrauch, 1978], and [Doyle, 1980]. Each presents a system capable of manipulating representations of its own program and current context. I argue that introspective ability is crucial for intelligent systems ??thout it an agent cannot represent certain problems that it must be able to solve. A theory of intelligent action would describe how and why certain actions intelligently achieve an agent's goals. The agent would both embody and represent this theory; it would be implemented as the program for the agent; and the importance of introspection suggests that the agent represent its theory of action to itself. 2004-10-04T14:54:01Z 2004-10-04T14:54:01Z 1983-02-01 AIM-701 http://hdl.handle.net/1721.1/6376 en_US AIM-701 11203946 bytes 8820228 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Batali, John Computational Introspection |
| title | Computational Introspection |
| title_full | Computational Introspection |
| title_fullStr | Computational Introspection |
| title_full_unstemmed | Computational Introspection |
| title_short | Computational Introspection |
| title_sort | computational introspection |
| url | http://hdl.handle.net/1721.1/6376 |
| work_keys_str_mv | AT batalijohn computationalintrospection |