Show simple item record

dc.contributor.advisorKnott, Alistair
dc.contributor.authorLee-Hand, Jeremy Sein Ong
dc.date.available2014-01-06T03:27:17Z
dc.date.copyright2013
dc.identifier.citationLee-Hand, J. S. O. (2013). A Neural Network Model of Causative Actions (Thesis, Master of Science). University of Otago. Retrieved from http://hdl.handle.net/10523/4549en
dc.identifier.urihttp://hdl.handle.net/10523/4549
dc.description.abstractMany of the actions we perform are defined by the effects they bring about, rather than as stereotypical sequences of motor movements. For instance, to open a door we must perform an action which results in the door opening. This thesis is a study of causative actions of this kind. I first introduce the class of causative actions, reviewing evidence for their existence from psychology, neuroscience and linguistics. I then present a computational model of motor control which can learn how to perform causative actions. The model I propose is an extension to an existing model in the literature (Oztop et al., 2004). In Oztop's model simple reach-to-grasp actions are learned through reinforcement using touch sensations which are considered to be intrinsically rewarding. In my extension, I propose that observed external events can also function as rewards if they are observed while the agent is executing a motor action and attending to the object being acted upon. I demonstrate the feasibility of this proposal in an implemented neural network model of causative actions. The model is also novel in that it does not require the trajectory of the hand to be precomputed. I conclude by discussing possible links between my model of causative actions and an account of the syntax of causative constructions in human language.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherUniversity of Otago
dc.rightsAll items in OUR Archive are provided for private study and research purposes and are protected by copyright with all rights reserved unless otherwise indicated.
dc.subjectMotor Learning
dc.subjectNeural Networks
dc.subjectLanguage
dc.subjectReinforcement Learning Rewards
dc.titleA Neural Network Model of Causative Actions
dc.typeThesis
dc.date.updated2013-12-29T13:39:57Z
dc.language.rfc3066en
thesis.degree.disciplineComputer Science
thesis.degree.nameMaster of Science
thesis.degree.grantorUniversity of Otago
thesis.degree.levelMasters
otago.openaccessOpen
 Find in your library

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record