Wexler, Mark (1996) Embodied induction: Learning external representations. [Conference Paper]
Full text available as:
![]()
|
Postscript
221Kb | |
![]() |
PDF
137Kb |
Abstract
The problem of inductive learning is hard, and--despite much work--no solution is in sight, from neural networks or other AI techniques. I suggest that inductive reasoning may be grounded in sensorimotor capacity. If an artificial system to generalize in ways that we find intelligent it should be appropriately embodied. This is illustrated with a network- controlled animat that learns n-parity by representing intermediate states with its own motion. Unlike other general learning devices, such as disembodied networks, it learns from very few examples and generalizes correctly to previously unseen cases.
Item Type: | Conference Paper |
---|---|
Keywords: | induction, inductive learning, generalization, action, external representations, machine learning, animats, n-parity problem |
Subjects: | Computer Science > Machine Learning Philosophy > Epistemology |
ID Code: | 515 |
Deposited By: | Wexler, Mark |
Deposited On: | 18 Sep 1998 |
Last Modified: | 11 Mar 2011 08:54 |
Metadata
- ASCII Citation
- Atom
- BibTeX
- Dublin Core
- EP3 XML
- EPrints Application Profile (experimental)
- EndNote
- HTML Citation
- ID Plus Text Citation
- JSON
- METS
- MODS
- MPEG-21 DIDL
- OpenURL ContextObject
- OpenURL ContextObject in Span
- RDF+N-Triples
- RDF+N3
- RDF+XML
- Refer
- Reference Manager
- Search Data Dump
- Simple Metadata
- YAML
Repository Staff Only: item control page