Learning Commonsense Categorical Knowledge in a Thread Memory System
If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have about the world. This endeavor suggests steps such as identifying...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/7114 |
| _version_ | 1811094500536221696 |
|---|---|
| author | Stamatoiu, Oana L. |
| author_facet | Stamatoiu, Oana L. |
| author_sort | Stamatoiu, Oana L. |
| collection | MIT |
| description | If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have about the world. This endeavor suggests steps such as identifying the kinds of knowledge people commonly have about the world, constructing suitable knowledge representations, and exploring the mechanisms that people use to make judgments about the everyday world. In this work, I contribute to these goals by proposing an architecture for a system that can learn commonsense knowledge about the properties and behavior of objects in the world. The architecture described here augments previous machine learning systems in four ways: (1) it relies on a seven dimensional notion of context, built from information recently given to the system, to learn and reason about objects' properties; (2) it has multiple methods that it can use to reason about objects, so that when one method fails, it can fall back on others; (3) it illustrates the usefulness of reasoning about objects by thinking about their similarity to other, better known objects, and by inferring properties of objects from the categories that they belong to; and (4) it represents an attempt to build an autonomous learner and reasoner, that sets its own goals for learning about the world and deduces new facts by reflecting on its acquired knowledge. This thesis describes this architecture, as well as a first implementation, that can learn from sentences such as ``A blue bird flew to the tree'' and ``The small bird flew to the cage'' that birds can fly. One of the main contributions of this work lies in suggesting a further set of salient ideas about how we can build broader purpose commonsense artificial learners and reasoners. |
| first_indexed | 2024-09-23T16:01:18Z |
| id | mit-1721.1/7114 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:01:18Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/71142019-04-10T11:52:39Z Learning Commonsense Categorical Knowledge in a Thread Memory System Stamatoiu, Oana L. AI learning context categorization similarity Bridge thread memory If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have about the world. This endeavor suggests steps such as identifying the kinds of knowledge people commonly have about the world, constructing suitable knowledge representations, and exploring the mechanisms that people use to make judgments about the everyday world. In this work, I contribute to these goals by proposing an architecture for a system that can learn commonsense knowledge about the properties and behavior of objects in the world. The architecture described here augments previous machine learning systems in four ways: (1) it relies on a seven dimensional notion of context, built from information recently given to the system, to learn and reason about objects' properties; (2) it has multiple methods that it can use to reason about objects, so that when one method fails, it can fall back on others; (3) it illustrates the usefulness of reasoning about objects by thinking about their similarity to other, better known objects, and by inferring properties of objects from the categories that they belong to; and (4) it represents an attempt to build an autonomous learner and reasoner, that sets its own goals for learning about the world and deduces new facts by reflecting on its acquired knowledge. This thesis describes this architecture, as well as a first implementation, that can learn from sentences such as ``A blue bird flew to the tree'' and ``The small bird flew to the cage'' that birds can fly. One of the main contributions of this work lies in suggesting a further set of salient ideas about how we can build broader purpose commonsense artificial learners and reasoners. 2004-10-20T20:32:25Z 2004-10-20T20:32:25Z 2004-05-18 AITR-2004-001 http://hdl.handle.net/1721.1/7114 en_US AITR-2004-001 96 p. 6550712 bytes 1993377 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI learning context categorization similarity Bridge thread memory Stamatoiu, Oana L. Learning Commonsense Categorical Knowledge in a Thread Memory System |
| title | Learning Commonsense Categorical Knowledge in a Thread Memory System |
| title_full | Learning Commonsense Categorical Knowledge in a Thread Memory System |
| title_fullStr | Learning Commonsense Categorical Knowledge in a Thread Memory System |
| title_full_unstemmed | Learning Commonsense Categorical Knowledge in a Thread Memory System |
| title_short | Learning Commonsense Categorical Knowledge in a Thread Memory System |
| title_sort | learning commonsense categorical knowledge in a thread memory system |
| topic | AI learning context categorization similarity Bridge thread memory |
| url | http://hdl.handle.net/1721.1/7114 |
| work_keys_str_mv | AT stamatoiuoanal learningcommonsensecategoricalknowledgeinathreadmemorysystem |