國立高雄大學圖資館 |

登入

回首頁

SHRUTI-agent :A structured connectionist architecture for reasoning and decision-making

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	SHRUTI-agent :
其他題名:	A structured connectionist architecture for reasoning and decision-making
作者:	Wendelken, John Carter.
面頁冊數:	282 p.
附註:	Co-Chairs: Lokendra Shastri; Jerome Feldman.
附註:	Source: Dissertation Abstracts International, Volume: 65-02, Section: B, page: 0853.
Contained By:	Dissertation Abstracts International65-02B.
標題:	Computer Science.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3121750
ISBN:	0496691015

SHRUTI-agent :A structured connectionist architecture for reasoning and decision-making
Wendelken, John Carter.

SHRUTI-agent :A structured connectionist architecture for reasoning and decision-making [electronic resource] - 282 p.

Co-Chairs: Lokendra Shastri; Jerome Feldman.

Thesis (Ph.D.)--University of California, Berkeley, 2003.

Creating a decision-making agent architecture based on SHRUTI involved a number of enhancements and additions to the SHRUTI model, and these comprise the primary contributions of the thesis. As a first step towards building an effective system for inference and decision-making, the evidential reasoning capability of the SHRUTI model was significantly enhanced. The resulting model demonstrates that relational knowledge and approximately probabilistic reasoning can be effectively combined in a connectionist architecture. Simple or reactive decision-making was made possible by the introduction into the model of compatible connectionist structures and mechanisms to represent and manipulate utility. It is shown that the basic decision-making capability of the model has much in common with formal methods from artificial intelligence. In order to enable the system to handle complex or sequential decision problems, a set of control mechanisms was developed. It is shown that the complex control mechanisms required for decision-making (e.g. hypothesis-testing) can be based on combinations of simple control primitives such as monitoring, filtering, and maintenance. Each of these control primitives is described in terms of its connectionist realization. Moreover, a subset of these control primitives are used as the basis for an implemented model of working memory in lateral prefrontal cortex. Operation of the SHRUTI-agent model is illustrated in two case studies, one involving simulated robot soccer and the other involving a military domain. Finally, consideration of the impact of learning on decision-making performance led to some preliminary work aimed at understanding how SHRUTI's structured representations can be learned. Utile concept learning is introduced as a mechanism for recruitment of new concepts and rules that lead to improved decision-making performance, and causal Hebbian learning is introduced as a mechanism for learning statistical causal rules.

ISBN: 0496691015Subjects--Topical Terms:

212513
Computer Science.

SHRUTI-agent :A structured connectionist architecture for reasoning and decision-making
LDR:03979nmm _2200325 _450 001 162454
005 20051017073448.5
008 230606s2003 eng d
020 $a 0496691015
035 $a 00148955
035 $a 162454
040 $a UnM $c UnM
100 0 $a Wendelken, John Carter. $3 227593
245 1 0 $a SHRUTI-agent : $b A structured connectionist architecture for reasoning and decision-making $h [electronic resource]
300 $a 282 p.
500 $a Co-Chairs: Lokendra Shastri; Jerome Feldman.
500 $a Source: Dissertation Abstracts International, Volume: 65-02, Section: B, page: 0853.
502 $a Thesis (Ph.D.)--University of California, Berkeley, 2003.
520 # $a Creating a decision-making agent architecture based on SHRUTI involved a number of enhancements and additions to the SHRUTI model, and these comprise the primary contributions of the thesis. As a first step towards building an effective system for inference and decision-making, the evidential reasoning capability of the SHRUTI model was significantly enhanced. The resulting model demonstrates that relational knowledge and approximately probabilistic reasoning can be effectively combined in a connectionist architecture. Simple or reactive decision-making was made possible by the introduction into the model of compatible connectionist structures and mechanisms to represent and manipulate utility. It is shown that the basic decision-making capability of the model has much in common with formal methods from artificial intelligence. In order to enable the system to handle complex or sequential decision problems, a set of control mechanisms was developed. It is shown that the complex control mechanisms required for decision-making (e.g. hypothesis-testing) can be based on combinations of simple control primitives such as monitoring, filtering, and maintenance. Each of these control primitives is described in terms of its connectionist realization. Moreover, a subset of these control primitives are used as the basis for an implemented model of working memory in lateral prefrontal cortex. Operation of the SHRUTI-agent model is illustrated in two case studies, one involving simulated robot soccer and the other involving a military domain. Finally, consideration of the impact of learning on decision-making performance led to some preliminary work aimed at understanding how SHRUTI's structured representations can be learned. Utile concept learning is introduced as a mechanism for recruitment of new concepts and rules that lead to improved decision-making performance, and causal Hebbian learning is introduced as a mechanism for learning statistical causal rules.
520 # $a One of the great scientific challenges of today is to understand how complex cognitive processes such as inference and decision-making can be achieved by the human brain. The incredible complexity of the brain makes computational modeling an indispensable tool to meet this challenge. Connectionist models that explain cognition in terms of brain-like structures and mechanisms are particularly useful in this endeavor.
520 # $a This thesis describes SHRUTI-agent, a neurally motivated, structured connectionist agent architecture that is capable of inference, decision-making, and interaction with a simulated environment. SHRUTI-agent is an extension of SHRUTI, a connectionist model that demonstrates how temporal synchrony variable binding in conjunction with structured, neurally plausible representations can support several aspects of high-level cognition.
590 $a School code: 0028.
650 # 0 $a Computer Science. $3 212513
650 # 0 $a Psychology, Cognitive. $3 212507
650 # 0 $a Biology, Neuroscience. $3 226972
690 $a 0317
690 $a 0633
690 $a 0984
710 0 # $a University of California, Berkeley. $3 212474
773 0 # $g 65-02B. $t Dissertation Abstracts International
790 $a 0028
790 1 0 $a Feldman, Jerome, $e advisor
790 1 0 $a Shastri, Lokendra, $e advisor
791 $a Ph.D.
792 $a 2003
856 4 0 $u http://libsw.nuk.edu.tw/login?url=http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3121750 $z http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3121750