國立高雄大學圖資館 |

Language: English

Back

Principles of noologytoward a theory...

Ho, Seng-Beng.

Principles of noologytoward a theory and science of intelligence /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Principles of noologyby Seng-Beng Ho.
Reminder of title:	toward a theory and science of intelligence /
Author:	Ho, Seng-Beng.
Published:	Cham :Springer International Publishing :2016.
Description:	xix, 431 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
Subject:	Artificial intelligence.
Online resource:	http://dx.doi.org/10.1007/978-3-319-32113-4
ISBN:	9783319321134$q(electronic bk.)

Principles of noologytoward a theory and science of intelligence /
Ho, Seng-Beng.

Principles of noologytoward a theory and science of intelligence /[electronic resource] :by Seng-Beng Ho. - Cham :Springer International Publishing :2016. - xix, 431 p. :ill., digital ;24 cm. - Socio-affective computing,v.32509-5706 ;. - Socio-affective computing ;v.1..

Preface -- Acknowledgement -- Introduction -- Rapid Unsupervised Effective Causal Learning -- A General Noological Framework -- Conceptual Grounding and Operational Representation -- Causal Rules, Problem Solving, and Operational Representation -- The Causal Role of Sensory Information -- Application to the StarCraft Game Environment -- A Grand Challenge for Noology and Computational Intelligence -- Affect Driven Noological Processes -- Summary and Beyond -- Appendix A: Causal vs Reinforcement Learning -- Appendix B: Rapid Effective Causal Learning Algorithm -- Index.

The idea of this book is to establish a new scientific discipline, "noology," under which a set of fundamental principles are proposed for the characterization of both naturally occurring and artificial intelligent systems. The methodology adopted in Principles of Noology for the characterization of intelligent systems, or "noological systems," is a computational one, much like that of AI. Many AI devices such as predicate logic representations, search mechanisms, heuristics, and computational learning mechanisms are employed but they are recast in a totally new framework for the characterization of noological systems. The computational approach in this book provides a quantitative and high resolution understanding of noological processes, and at the same time the principles and methodologies formulated are directly implementable in AI systems. In contrast to traditional AI that ignores motivational and affective processes, under the paradigm of noology, motivational and affective processes are central to the functioning of noological systems and their roles in noological processes are elucidated in detailed computational terms. In addition, a number of novel representational and learning mechanisms are proposed, and ample examples and computer simulations are provided to show their applications. These include rapid effective causal learning (a novel learning mechanism that allows an AI/noological system to learn causality with a small number of training instances), learning of scripts that enables knowledge chunking and rapid problem solving, and learning of heuristics that further accelerates problem solving. Semantic grounding allows an AI/noological system to "truly understand" the meaning of the knowledge it encodes. This issue is extensively explored. This is a highly informative book providing novel and deep insights into intelligent systems which is particularly relevant to both researchers and students of AI and the cognitive sciences.

ISBN: 9783319321134$q(electronic bk.)

Standard No.: 10.1007/978-3-319-32113-4doiSubjects--Topical Terms:

194058
Artificial intelligence.

LC Class. No.: Q335

Dewey Class. No.: 006.3

Principles of noologytoward a theory and science of intelligence /
LDR:03556nmm a2200325 a 4500 001 490225
003 DE-He213
005 20161111160454.0
006 m d
007 cr nn 008maaau
008 170118s2016 gw s 0 eng d
020 $a 9783319321134$q(electronic bk.)
020 $a 9783319321110$q(paper)
024 7 $a 10.1007/978-3-319-32113-4 $2 doi
035 $a 978-3-319-32113-4
040 $a GP $c GP
041 0 $a eng
050 4 $a Q335
072 7 $a PSAN $2 bicssc
072 7 $a MED057000 $2 bisacsh
082 0 4 $a 006.3 $2 23
090 $a Q335 $b .H678 2016
100 1 $a Ho, Seng-Beng. $3 749554
245 1 0 $a Principles of noology $h [electronic resource] : $b toward a theory and science of intelligence / $c by Seng-Beng Ho.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2016.
300 $a xix, 431 p. : $b ill., digital ; $c 24 cm.
490 1 $a Socio-affective computing, $x 2509-5706 ; $v v.3
505 0 $a Preface -- Acknowledgement -- Introduction -- Rapid Unsupervised Effective Causal Learning -- A General Noological Framework -- Conceptual Grounding and Operational Representation -- Causal Rules, Problem Solving, and Operational Representation -- The Causal Role of Sensory Information -- Application to the StarCraft Game Environment -- A Grand Challenge for Noology and Computational Intelligence -- Affect Driven Noological Processes -- Summary and Beyond -- Appendix A: Causal vs Reinforcement Learning -- Appendix B: Rapid Effective Causal Learning Algorithm -- Index.
520 $a The idea of this book is to establish a new scientific discipline, "noology," under which a set of fundamental principles are proposed for the characterization of both naturally occurring and artificial intelligent systems. The methodology adopted in Principles of Noology for the characterization of intelligent systems, or "noological systems," is a computational one, much like that of AI. Many AI devices such as predicate logic representations, search mechanisms, heuristics, and computational learning mechanisms are employed but they are recast in a totally new framework for the characterization of noological systems. The computational approach in this book provides a quantitative and high resolution understanding of noological processes, and at the same time the principles and methodologies formulated are directly implementable in AI systems. In contrast to traditional AI that ignores motivational and affective processes, under the paradigm of noology, motivational and affective processes are central to the functioning of noological systems and their roles in noological processes are elucidated in detailed computational terms. In addition, a number of novel representational and learning mechanisms are proposed, and ample examples and computer simulations are provided to show their applications. These include rapid effective causal learning (a novel learning mechanism that allows an AI/noological system to learn causality with a small number of training instances), learning of scripts that enables knowledge chunking and rapid problem solving, and learning of heuristics that further accelerates problem solving. Semantic grounding allows an AI/noological system to "truly understand" the meaning of the knowledge it encodes. This issue is extensively explored. This is a highly informative book providing novel and deep insights into intelligent systems which is particularly relevant to both researchers and students of AI and the cognitive sciences.
650 0 $a Artificial intelligence. $3 194058
650 0 $a Computational neuroscience. $3 190429
650 0 $a Medicine. $3 193819
650 0 $a Science. $3 177564
650 0 $a Neurosciences. $3 211508
650 0 $a Computational intelligence. $3 210824
650 1 4 $a Biomedicine. $3 273648
650 2 4 $a Artificial Intelligence (incl. Robotics) $3 252959
650 2 4 $a Computational Intelligence. $3 338479
650 2 4 $a Science, general. $3 274924
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
830 0 $a Socio-affective computing ; $v v.1. $3 732529
856 4 0 $u http://dx.doi.org/10.1007/978-3-319-32113-4
950 $a Biomedical and Life Sciences (Springer-11642)