@misc{cogprints515, editor = {Maja Mataric}, title = {Embodied induction: Learning external representations}, author = {Mark Wexler}, publisher = {AAAI Press}, year = {1996}, pages = {134--138}, keywords = {induction, inductive learning, generalization, action, external representations, machine learning, animats, n-parity problem}, url = {http://cogprints.org/515/}, 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.} }