Truth from trash how learning makes sense /
This study of learning in autonomous agents offers a bracing intellectual adventure. Chris Thornton makes the compelling claim that learning is not a passive discovery operation but an active process involving creativity on the part of the learner. Although theorists of machine learning tell us that...
| Main Author: | Thornton, Christopher James. |
|---|---|
| Other Authors: | EBSCOhost. |
| Format: | eBook |
| Language: | English |
| Published: |
Cambridge, MA :
MIT Press,
[2000]
|
| Physical Description: |
1 online resource (x, 204 pages) : illustrations. |
| Series: |
Complex adaptive systems.
|
| Subjects: |
| Summary: |
This study of learning in autonomous agents offers a bracing intellectual adventure. Chris Thornton makes the compelling claim that learning is not a passive discovery operation but an active process involving creativity on the part of the learner. Although theorists of machine learning tell us that all learning methods contribute some form of bias and thus involve a degree of creativity, Thornton carries the idea much further. He describes an incremental process, recursive relational learning, in which the results of one learning step serve as the basis for the next. Very high-level recodings are then substantially the creative artifacts of the learner's own processing. Lower-level recodings are more "objective" in that their properties are more severely constrained by the source data. Thornton sees consciousness as a process at the outer fringe of relational learning, just prior to the onset of creativity. According to this view, we cannot assume consciousness to be an exclusively human phenomenon, but rather the expected feature of any cognitive mechanism able to engage in extended flights of relational learning. Thornton presents key background material in an entertaining manner, using extensive mental imagery and a minimum of mathematics. Anecdotes and dialogue add to the text's informality. |
|---|---|
| Item Description: |
Includes bibliographical references (pages 199-201) and index. Preface -- 1. Machine That Could Learn Anything -- 2. Consider Thy Neighbor -- 3. Kepler on Mars -- 4. Information Chicane -- 5. Fence-and-Fill Learning -- 6. Turing and the Submarines -- 7. Relational Gulf -- 8. Supercharged Learner -- 9. David Hume and the Crash of '87 -- 10. Phases of Compression -- 11. Protorepresentational Learning -- 12. Creativity Continuum -- References -- Index. This study of learning in autonomous agents offers a bracing intellectual adventure. Chris Thornton makes the compelling claim that learning is not a passive discovery operation but an active process involving creativity on the part of the learner. Although theorists of machine learning tell us that all learning methods contribute some form of bias and thus involve a degree of creativity, Thornton carries the idea much further. He describes an incremental process, recursive relational learning, in which the results of one learning step serve as the basis for the next. Very high-level recodings are then substantially the creative artifacts of the learner's own processing. Lower-level recodings are more "objective" in that their properties are more severely constrained by the source data. Thornton sees consciousness as a process at the outer fringe of relational learning, just prior to the onset of creativity. According to this view, we cannot assume consciousness to be an exclusively human phenomenon, but rather the expected feature of any cognitive mechanism able to engage in extended flights of relational learning. Thornton presents key background material in an entertaining manner, using extensive mental imagery and a minimum of mathematics. Anecdotes and dialogue add to the text's informality. Access restricted to York University faculty, staff and students. English. Colorado Mountain College - E-book Collection / Ebsco. Colorado Mountain College - E-book Collection / Ebsco Academic. |
| Physical Description: |
1 online resource (x, 204 pages) : illustrations. |
| Bibliography: |
Includes bibliographical references (pages 199-201) and index. |
| ISBN: |
0585263809 9780585263809 9780262201278 0262201275 0262700875 9780262700870 9780262284981 0262284987 |
| Access: |
Access restricted to York University faculty, staff and students. |