FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2516451882> ?p ?o ?g. }

• W2516451882 endingPage "148" @default.
• W2516451882 startingPage "148" @default.
• W2516451882 abstract "In this dissertation, we investigate by observation , a machine approach to create cognitive agents automatically by observing the task-performance behavior of human experts. We argue that the most important challenge of by observation is that the internal reasoning of the expert is not available to the learner. As a solution, we propose a framework that uses multiple complex knowledge sources to model the expert more accurately. We describe a relational by observation framework that uses expert behavior traces and expert goal annotations as the primary input, interprets them in the context of background knowledge, inductively finds patterns in similar expert decisions, and creates an agent program. The background knowledge used to interpret the expert behavior does not only include task and domain knowledge, but also domain independent by observation knowledge that models the fixed mental mechanisms of the expert. We explore two approaches. In from behavior performances approach, the main source of information used in is behavior traces of expert recorded during actual task performance. In the from diagrammatic behavior specifications approach, the expert specifies behavior using a graphical representation, abstractly depicting the critical situations for the desired behavior. This provides the expert with additional modes of interaction with the system; simplifying the task at the expense of more expert effort. Both of these approaches are uniformly represented in relational by observation framework. Our framework maps an agent problem on to multiple problems that can be represented in a supervised concept learning setting. The acquired procedural knowledge is partitioned into a hierarchy of goals and it is represented with first order rules. Using an inductive logic programming (ILP) component allows our system to combine complex knowledge from multiple sources. These sources include the behavior traces, which are temporally changing relational situations, the expert goal annotations, which are hierarchically organized and provide structured information, and background knowledge, which is represented as relational facts and first order rules. Our by observation framework needs to store large amounts of behavior data and access it efficiently during learning. We propose an episodic database as a solution, which is an extension of Prolog that improves Prolog by providing efficient and power mechanisms to store and query relational temporal information. We evaluated our framework using both artificially created examples and behavior observation traces generated by AI agents. We developed a general methodology to test relational by observation. Our methodology is based on first using a hand-coded agent program as the expert, and then comparing the decision making knowledge of the expert and learned agent programs on observed situations." @default.
• W2516451882 created "2016-09-16" @default.
• W2516451882 creator A5061159721 @default.
• W2516451882 creator A5090457873 @default.
• W2516451882 date "2007-01-01" @default.
• W2516451882 modified "2023-09-27" @default.
• W2516451882 title "Relational learning by observation" @default.
• W2516451882 cites W101172001 @default.
• W2516451882 cites W1488252886 @default.
• W2516451882 cites W1490861665 @default.
• W2516451882 cites W1496915410 @default.
• W2516451882 cites W1500444450 @default.
• W2516451882 cites W150885707 @default.
• W2516451882 cites W1511887321 @default.
• W2516451882 cites W1512637950 @default.
• W2516451882 cites W1516870318 @default.
• W2516451882 cites W1531110464 @default.
• W2516451882 cites W1538741148 @default.
• W2516451882 cites W1564663916 @default.
• W2516451882 cites W1572710235 @default.
• W2516451882 cites W1599152640 @default.
• W2516451882 cites W160274533 @default.
• W2516451882 cites W16599163 @default.
• W2516451882 cites W1808725644 @default.
• W2516451882 cites W1905489673 @default.
• W2516451882 cites W1966028617 @default.
• W2516451882 cites W1977546238 @default.
• W2516451882 cites W1987902506 @default.
• W2516451882 cites W198956113 @default.
• W2516451882 cites W1990300548 @default.
• W2516451882 cites W2023301330 @default.
• W2516451882 cites W2062122188 @default.
• W2516451882 cites W2088563966 @default.
• W2516451882 cites W2094353543 @default.
• W2516451882 cites W2100656766 @default.
• W2516451882 cites W2111038026 @default.
• W2516451882 cites W2119831128 @default.
• W2516451882 cites W2120684076 @default.
• W2516451882 cites W2127650263 @default.
• W2516451882 cites W2128420091 @default.
• W2516451882 cites W2162227979 @default.
• W2516451882 cites W2163274265 @default.
• W2516451882 cites W2163445345 @default.
• W2516451882 cites W2170396035 @default.
• W2516451882 cites W2171425630 @default.
• W2516451882 cites W2174803659 @default.
• W2516451882 cites W2177109876 @default.
• W2516451882 cites W2180809782 @default.
• W2516451882 cites W2180885055 @default.
• W2516451882 cites W2337392266 @default.
• W2516451882 cites W27427315 @default.
• W2516451882 cites W3020831056 @default.
• W2516451882 cites W37034129 @default.
• W2516451882 cites W40291581 @default.
• W2516451882 cites W7785909 @default.
• W2516451882 cites W2526239646 @default.
• W2516451882 hasPublicationYear "2007" @default.
• W2516451882 type Work @default.
• W2516451882 sameAs 2516451882 @default.
• W2516451882 citedByCount "0" @default.
• W2516451882 crossrefType "dissertation" @default.
• W2516451882 hasAuthorship W2516451882A5061159721 @default.
• W2516451882 hasAuthorship W2516451882A5090457873 @default.
• W2516451882 hasConcept C102600418 @default.
• W2516451882 hasConcept C105002631 @default.
• W2516451882 hasConcept C106624574 @default.
• W2516451882 hasConcept C107457646 @default.
• W2516451882 hasConcept C119857082 @default.
• W2516451882 hasConcept C124469403 @default.
• W2516451882 hasConcept C127413603 @default.
• W2516451882 hasConcept C134306372 @default.
• W2516451882 hasConcept C151730666 @default.
• W2516451882 hasConcept C154945302 @default.
• W2516451882 hasConcept C162324750 @default.
• W2516451882 hasConcept C17744445 @default.
• W2516451882 hasConcept C199360897 @default.
• W2516451882 hasConcept C199539241 @default.
• W2516451882 hasConcept C201995342 @default.
• W2516451882 hasConcept C207685749 @default.
• W2516451882 hasConcept C2776359362 @default.
• W2516451882 hasConcept C2779343474 @default.
• W2516451882 hasConcept C2780451532 @default.
• W2516451882 hasConcept C31170391 @default.
• W2516451882 hasConcept C33923547 @default.
• W2516451882 hasConcept C34447519 @default.
• W2516451882 hasConcept C36503486 @default.
• W2516451882 hasConcept C41008148 @default.
• W2516451882 hasConcept C58328972 @default.
• W2516451882 hasConcept C86803240 @default.
• W2516451882 hasConcept C94625758 @default.
• W2516451882 hasConceptScore W2516451882C102600418 @default.
• W2516451882 hasConceptScore W2516451882C105002631 @default.
• W2516451882 hasConceptScore W2516451882C106624574 @default.
• W2516451882 hasConceptScore W2516451882C107457646 @default.
• W2516451882 hasConceptScore W2516451882C119857082 @default.
• W2516451882 hasConceptScore W2516451882C124469403 @default.
• W2516451882 hasConceptScore W2516451882C127413603 @default.
• W2516451882 hasConceptScore W2516451882C134306372 @default.

• next