國立虎尾科技大學 |

Evolvable Mathematical Models : = A New Artificial Intelligence Paradigm.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Evolvable Mathematical Models :/
Reminder of title:	A New Artificial Intelligence Paradigm.
Author:	Grouchy, Paul.
Description:	1 online resource (151 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.
Subject:	Artificial intelligence. -
Online resource:	click for full text (PQDT)
ISBN:	9781339372518

Evolvable Mathematical Models : = A New Artificial Intelligence Paradigm.
Grouchy, Paul.

Evolvable Mathematical Models :A New Artificial Intelligence Paradigm. - 1 online resource (151 pages)

Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.

Thesis (Ph.D.)--University of Toronto (Canada), 2014.

Includes bibliographical references

We develop a novel Artificial Intelligence paradigm to generate autonomously artificial agents as mathematical models of behaviour. Agent/environment inputs are mapped to agent outputs via equation trees which are evolved in a manner similar to Symbolic Regression in Genetic Programming. Equations are comprised of only the four basic mathematical operators, addition, subtraction, multiplication and division, as well as input and output variables and constants. From these operations, equations can be constructed that approximate any analytic function. These Evolvable Mathematical Models (EMMs) are tested and compared to their Artificial Neural Network (ANN) counterparts on two benchmarking tasks: the double-pole balancing without velocity information benchmark and the challenging discrete Double-T Maze experiments with homing. The results from these experiments show that EMMs are capable of solving tasks typically solved by ANNs, and that they have the ability to produce agents that demonstrate learning behaviours. To further explore the capabilities of EMMs, as well as to investigate the evolutionary origins of communication, we develop NoiseWorld, an Artificial Life simulation in which interagent communication emerges and evolves from initially noncommunicating EMM-based agents. Agents develop the capability to transmit their x and y position information over a one-dimensional channel via a complex, dialogue-based communication scheme. These evolved communication schemes are analyzed and their evolutionary trajectories examined, yielding significant insight into the emergence and subsequent evolution of cooperative communication. Evolved agents from NoiseWorld are successfully transferred onto physical robots, demonstrating the transferability of EMM-based AIs from simulation into physical reality.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781339372518Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Evolvable Mathematical Models : = A New Artificial Intelligence Paradigm.
LDR:02966ntm a2200313K 4500 001 913807
005 20180622095237.5
006 m o u
007 cr mn||||a|a||
008 190606s2014 xx obm 000 0 eng d
020 $a 9781339372518
035 $a (MiAaPQ)AAI3744466
035 $a AAI3744466
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Grouchy, Paul. $3 1186799
245 1 0 $a Evolvable Mathematical Models : $b A New Artificial Intelligence Paradigm.
264 0 $c 2014
300 $a 1 online resource (151 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.
500 $a Adviser: Gabriele M. T. D'Eleuterio.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2014.
504 $a Includes bibliographical references
520 $a We develop a novel Artificial Intelligence paradigm to generate autonomously artificial agents as mathematical models of behaviour. Agent/environment inputs are mapped to agent outputs via equation trees which are evolved in a manner similar to Symbolic Regression in Genetic Programming. Equations are comprised of only the four basic mathematical operators, addition, subtraction, multiplication and division, as well as input and output variables and constants. From these operations, equations can be constructed that approximate any analytic function. These Evolvable Mathematical Models (EMMs) are tested and compared to their Artificial Neural Network (ANN) counterparts on two benchmarking tasks: the double-pole balancing without velocity information benchmark and the challenging discrete Double-T Maze experiments with homing. The results from these experiments show that EMMs are capable of solving tasks typically solved by ANNs, and that they have the ability to produce agents that demonstrate learning behaviours. To further explore the capabilities of EMMs, as well as to investigate the evolutionary origins of communication, we develop NoiseWorld, an Artificial Life simulation in which interagent communication emerges and evolves from initially noncommunicating EMM-based agents. Agents develop the capability to transmit their x and y position information over a one-dimensional channel via a complex, dialogue-based communication scheme. These evolved communication schemes are analyzed and their evolutionary trajectories examined, yielding significant insight into the emergence and subsequent evolution of cooperative communication. Evolved agents from NoiseWorld are successfully transferred onto physical robots, demonstrating the transferability of EMM-based AIs from simulation into physical reality.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer engineering. $3 569006
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Toronto (Canada). $b Aerospace Engineering. $3 1186800
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3744466 $z click for full text (PQDT)