BUILDING AN ARTIFICIAL CEREBELLUM USING A SYSTEM OF DISTRIBUTED Q-LEARNING AGENTS

Persistent Link:
http://hdl.handle.net/10150/194811
Title:
BUILDING AN ARTIFICIAL CEREBELLUM USING A SYSTEM OF DISTRIBUTED Q-LEARNING AGENTS
Author:
Soto Santibanez, Miguel Angel
Issue Date:
2010
Publisher:
The University of Arizona.
Rights:
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract:
About 400 million years ago sharks developed a separate co-processor in their brains that not only made them faster but also more precisely coordinated. This co-processor, which is nowadays called cerebellum, allowed sharks to outperform their peers and survive as one of the fittest. For the last 40 years or so, researchers have been attempting to provide robots and other machines with this type of capability. This thesis discusses currently used methods to create artificial cerebellums and points out two main shortcomings: 1) framework usability issues and 2) building blocks incompatibility issues. This research argues that the framework usability issues hinder the production of good quality artificial cerebellums for a large number of applications. Furthermore, this study argues that the building blocks incompatibility issues make artificial cerebellums less efficient that they could be, given our current technology. To tackle the framework usability issues, this thesis research proposes the use of a new framework, which formalizes the task of creating artificial cerebellums and offers a list of simple steps to accomplish this task. Furthermore, to tackle the building blocks incompatibility issues, this research proposes thinking of artificial cerebellums as a set of cooperating q-learning agents, which utilize a new technique called Moving Prototypes to make better use of the available memory and computational resources. Furthermore, this work describes a set of general guidelines that can be applied to accelerate the training of this type of system. Simulation is used to show examples of the performance improvements resulting from the use of these guidelines. To illustrate the theory developed in this dissertation, this paper implements a cerebellum for a real life application, namely, a cerebellum capable of controlling a type of mining equipment called front-end loader. Finally, this thesis proposes the creation of a development tool based on this formalization. This research argues that such a development tool would allow engineers, scientists and technicians to quickly build customized cerebellums for a wide range of applications without the need of becoming experts on the area of Artificial Intelligence, Neuroscience or Machine Learning.
Type:
text; Electronic Dissertation
Keywords:
Artificial; Cerebellum; Distributed; Q-learning
Degree Name:
Ph.D.
Degree Level:
doctoral
Degree Program:
Electrical & Computer Engineering; Graduate College
Degree Grantor:
University of Arizona
Committee Chair:
Cellier, Francois E.; Hariri, Salim

Full metadata record

DC FieldValue Language
dc.language.isoenen_US
dc.titleBUILDING AN ARTIFICIAL CEREBELLUM USING A SYSTEM OF DISTRIBUTED Q-LEARNING AGENTSen_US
dc.creatorSoto Santibanez, Miguel Angelen_US
dc.contributor.authorSoto Santibanez, Miguel Angelen_US
dc.date.issued2010en_US
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.description.abstractAbout 400 million years ago sharks developed a separate co-processor in their brains that not only made them faster but also more precisely coordinated. This co-processor, which is nowadays called cerebellum, allowed sharks to outperform their peers and survive as one of the fittest. For the last 40 years or so, researchers have been attempting to provide robots and other machines with this type of capability. This thesis discusses currently used methods to create artificial cerebellums and points out two main shortcomings: 1) framework usability issues and 2) building blocks incompatibility issues. This research argues that the framework usability issues hinder the production of good quality artificial cerebellums for a large number of applications. Furthermore, this study argues that the building blocks incompatibility issues make artificial cerebellums less efficient that they could be, given our current technology. To tackle the framework usability issues, this thesis research proposes the use of a new framework, which formalizes the task of creating artificial cerebellums and offers a list of simple steps to accomplish this task. Furthermore, to tackle the building blocks incompatibility issues, this research proposes thinking of artificial cerebellums as a set of cooperating q-learning agents, which utilize a new technique called Moving Prototypes to make better use of the available memory and computational resources. Furthermore, this work describes a set of general guidelines that can be applied to accelerate the training of this type of system. Simulation is used to show examples of the performance improvements resulting from the use of these guidelines. To illustrate the theory developed in this dissertation, this paper implements a cerebellum for a real life application, namely, a cerebellum capable of controlling a type of mining equipment called front-end loader. Finally, this thesis proposes the creation of a development tool based on this formalization. This research argues that such a development tool would allow engineers, scientists and technicians to quickly build customized cerebellums for a wide range of applications without the need of becoming experts on the area of Artificial Intelligence, Neuroscience or Machine Learning.en_US
dc.typetexten_US
dc.typeElectronic Dissertationen_US
dc.subjectArtificialen_US
dc.subjectCerebellumen_US
dc.subjectDistributeden_US
dc.subjectQ-learningen_US
thesis.degree.namePh.D.en_US
thesis.degree.leveldoctoralen_US
thesis.degree.disciplineElectrical & Computer Engineeringen_US
thesis.degree.disciplineGraduate Collegeen_US
thesis.degree.grantorUniversity of Arizonaen_US
dc.contributor.chairCellier, Francois E.en_US
dc.contributor.chairHariri, Salimen_US
dc.contributor.committeememberZeigler, Bernard P.en_US
dc.identifier.proquest11322en_US
dc.identifier.oclc752261173en_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.