Cogprints

Embodied induction: Learning external representations

Wexler, Mark (1996) Embodied induction: Learning external representations. [Conference Paper]

Full text available as:

[img]
Preview
Postscript
221Kb
[img]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

Repository Staff Only: item control page