DMCA
1A neural network model of causative actions
BibTeX
@MISC{Lee-h_1aneural,
author = {Jeremy Lee-h and Alistair Knott and Jeremy Lee-h and Alistair Knott},
title = {1A neural network model of causative actions},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper we present a neural network model of motor learning and motor control that learns a class of actions termed causative actions. A causative action is an action that brings about a specified effect or movement in a target object: for instance the action of causing a lever to bend, or of causing a door to open. The network comprises a layered set of motor learning circuits that associate motor actions with their sensory effects, as proposed by Hommel et al. [1]. The circuit for learning simple manual actions is trained by sensory representations in the haptic modality that function as rewards, as previously proposed by Oztop and Arbib [2]. We propose that the circuit responsible for learning causative actions makes similar use of sensory representations as reward signals. The key novel idea is that the sensory representations in this case come not from the tactile system, but from a high-level perceptual module that registers arbitrary movements taking place in external objects in the world.
Keyphrases
causative action neural network model sensory representation tactile system reward signal simple manual action haptic modality motor learning specified effect external object key novel idea similar use target object motor action sensory effect register arbitrary movement motor control high-level perceptual module layered set
