creators_name: Lan, Tian
creators_name: Arnold, Michael
creators_name: Sejnowski, Terrence
creators_name: Jabri, Marwan
editors_name: Prince, Christopher G.
editors_name: Berthouze, Luc
editors_name: Kozima, Hideki
editors_name: Bullock, Daniel
editors_name: Stojanov, Georgi
editors_name: Balkenius, Christian
type: confposter
datestamp: 2004-02-12
lastmod: 2011-03-11 08:55:26
metadata_visibility: show
title: A biologically inspired computational model of the Block Copying Task
ispublished: pub
subjects: comp-sci-mach-learn
subjects: comp-sci-neural-nets
full_text_status: public
keywords: block copying task, basal ganglia model, actor-critic architecture, temporal difference learning
abstract: We present in this paper a biologically inspired model of the Basal Ganglia which deals with Block Copying as a sequence learning task. By breaking a relatively complex task into simpler operations with well-defined skills, an approach which is termed as a skill-based machine design is used in the device of computational models to complete such tasks. Basal Ganglia are critically involved in sensorimotor control. From the learning aspects, Actor-Critic architectures have been proposed to model the Basal Ganglia and Temporal difference has been proposed as a learning algorithm. The model is implemented and simulation results are presented to show the capability of our model to successfully complete the task.
date: 2003
date_type: published
volume: 101
publisher: Lund University Cognitive Studies
pagerange: 171-172
refereed: TRUE
citation:   Lan, Tian and Arnold, Michael and Sejnowski, Terrence and Jabri, Marwan  (2003) A biologically inspired computational model of the Block Copying Task.  [Conference Poster]     
document_url: http://cogprints.org/3350/1/Lan.pdf