Tools

LEADER 03465cam a2200493Ia 4500

001 ocn648765028;

003 OCoLC;

005 20141212052053.0;

006 m d ;

007 cr bn|||||||||;

008 100719s2009 ncua ob 000 0 eng d;

035 a| (Sirsi) o648765028;

035 a| (OCoLC)648765028;

040 a| EREc| EREd| EREd| UtOrBLW;

049 a| EREE;

090 a| QA76.87;

100 1 a| Ahlstrom, Mark.?| UNAUTHORIZED;

245 10 a| Recurrence and plasticity in evolved adaptive neural controllers /c| by Mark Ahlstrom.;

260 a| [Greenville, N.C.] :b| East Carolina University,c| 2009.;

300 a| 122 pages :b| ills. (some color), digital, PDF file;

336 a| text2| rdacontent;

337 a| computer2| rdamedia;

338 a| online resource2| rdacarrier;

500 a| Presented to the faculty of the Department of Computer Science.;

500 a| Advisor: M.H.N. Tabrizi.;

500 a| Title from PDF t.p. (viewed July 21, 2010).;

502 b| M.S.c| East Carolina Universityd| 2009.;

504 a| Includes bibliographical references.;

520 3 a| Among the more important applications of evolutionary neurocontrollers is the development of systems that are able to dynamically adapt to a changing environment. While traditional approaches to control system design demand that the developer attempt to foresee all possible situations within which the controller may operate, neuroevolutionary approaches can facilitate the design of systems that are capable of operating in unforeseen circumstances. This paper examines two methods that have been used to provide for this adaptivity. The first method is the use of recurrent neural networks that have fixed connection weights. The second develops neurocontrollers with plastic synapses, thus allowing for the adaptation of the connection weights. Previous experimental results have shown that while both approaches can facilitate adaptive behavior, neural plasticity does not necessarily confer the expected benefits. In experiments using the NeuroEvolution of Augmenting Topologies (NEAT) method, Stanley et al. (2003) discovered that in simple cases, recurrence was sufficient in solving at least some control problems. I examined whether or not these initial results continue to scale upwards into more complex problem spaces. This was done through a series of experiments ranging from controlling a simplified cannon shot to attempting to evolve neural flight controllers capable of flying different airplanes through a series of waypoints. The results of these experiments indicate that the NEAT algorithm itself is unable to scale efficiently to some larger problem spaces.;

538 a| System requirements: Adobe Reader.;

538 a| Mode of access: World Wide Web.;

650 0 a| Neural networks (Computer science)=| ^A263002;

650 0 a| Computer networks.=| ^A21418;

650 0 a| Evolutionary computation.=| ^A494376;

653 a| Computer Science;

700 1 a| Tabrizi, M. H. N.?| UNAUTHORIZED;

710 2 a| East Carolina University.b| Department of Computer Science.?| UNAUTHORIZED;

856 40 z| Access via ScholarShipu| http://hdl.handle.net/10342/2658;

949 o| jgml;

994 a| C0b| ERE;

596 a| 1 4;

998 a| 2284716;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 2284716-1001l| JNETm| JOYNERr| Ys| Yt| JNE3ETDu| 7/19/2010x| ETDz| JERESOURCE;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 2284716-2001l| HSLELECm| HSLr| Ys| Yt| HEETDu| 7/19/2010x| ETDz| HERESOURCE;

Recurrence and plasticity in evolved adaptive neural controllers / by Mark Ahlstrom.

Author/creator	Ahlstrom, Mark
Other author	Tabrizi, M. H. N.
Other author	East Carolina University. Department of Computer Science.
Format	Theses and dissertations
Publication Info	[Greenville, N.C.] : East Carolina University, 2009.
Description	122 pages : ills. (some color), digital, PDF file
Supplemental Content	Access via ScholarShip
Subjects	Neural networks (Computer science) Computer networks. Evolutionary computation.

Summary	Among the more important applications of evolutionary neurocontrollers is the development of systems that are able to dynamically adapt to a changing environment. While traditional approaches to control system design demand that the developer attempt to foresee all possible situations within which the controller may operate, neuroevolutionary approaches can facilitate the design of systems that are capable of operating in unforeseen circumstances. This paper examines two methods that have been used to provide for this adaptivity. The first method is the use of recurrent neural networks that have fixed connection weights. The second develops neurocontrollers with plastic synapses, thus allowing for the adaptation of the connection weights. Previous experimental results have shown that while both approaches can facilitate adaptive behavior, neural plasticity does not necessarily confer the expected benefits. In experiments using the NeuroEvolution of Augmenting Topologies (NEAT) method, Stanley et al. (2003) discovered that in simple cases, recurrence was sufficient in solving at least some control problems. I examined whether or not these initial results continue to scale upwards into more complex problem spaces. This was done through a series of experiments ranging from controlling a simplified cannon shot to attempting to evolve neural flight controllers capable of flying different airplanes through a series of waypoints. The results of these experiments indicate that the NEAT algorithm itself is unable to scale efficiently to some larger problem spaces.
General note	Presented to the faculty of the Department of Computer Science.
General note	Advisor: M.H.N. Tabrizi.
General note	Title from PDF t.p. (viewed July 21, 2010).
Dissertation note	M.S. East Carolina University 2009.
Bibliography note	Includes bibliographical references.
Technical details	System requirements: Adobe Reader.
Technical details	Mode of access: World Wide Web.

Availability

Library	Location	Call Number	Status	Item Actions
	Electronic Resources	Access Content Online	✔ Available

Recurrence and plasticity in evolved adaptive neural controllers / by Mark Ahlstrom.

Click here for more information about this title

Availability