scholarly journals Acting and Learning with Goal and Task Decomposition

2021 ◽  
Author(s):  
◽  
Maciej Wojnar
Keyword(s):  
Intelligent Agents ◽  
Domain Knowledge ◽  
Learning System ◽  
Planning System ◽  
Unexpected Events ◽  
Routine Tasks ◽  
The Face ◽  
Rule Set ◽  
Human World ◽  
And Task

<p><b>Two central problems of creating artificial intelligent agents that can operate in the human world are learning the necessary knowledge to achieve routine tasks, and using that knowledge effectively in a complex and unpredictable domain. The thesis argues that an important part of this domain knowledge should be represented in the form of decomposition rules that decompose tasks into subgoals. The thesis presents HOPPER, an implemented planning system that uses decomposition rules and a least-commitment decomposition strategy that strikes a balance between reactive and deliberative planning. Like reactive planners, HOPPER is able to robustly handle and recover from unexpected events with minimal disruption to its plan. Like deliberative planners, it is also able to plan ahead to take advantage of opportunities to interleave and shorten its sub-plans. The thesis also presents TADPOLE, an implemented learning system that learns both the structure and preconditions of new decomposition rules from a small number of lessons demonstrated by a teacher. It learns by parsing and interpreting the teacher’s behaviour in terms of decomposition rules it already knows. It extends its rule set by filling in the holes in its parses of the teacher’s lessons.</b></p> <p>Both HOPPER and TADPOLE have been evaluated together in two different domains: a kitchen domain that emphasizes complexity, and a logistics domain that emphasizes plan efficiency. Every rule used by HOPPER was learned by TADPOLE and every rule learned by TADPOLE was successfully used by HOPPER to achieve various tasks, showing that TADPOLE is able to learn effective decomposition rules from minimal lessons from a teacher, and that HOPPER is able to robustly make use of them even in the face of unexpected events.</p>

scholarly journals Acting and Learning with Goal and Task Decomposition

2021 ◽  
Author(s):  
◽  
Maciej Wojnar
Keyword(s):  
Intelligent Agents ◽  
Domain Knowledge ◽  
Learning System ◽  
Planning System ◽  
Unexpected Events ◽  
Routine Tasks ◽  
The Face ◽  
Rule Set ◽  
Human World ◽  
And Task

<p><b>Two central problems of creating artificial intelligent agents that can operate in the human world are learning the necessary knowledge to achieve routine tasks, and using that knowledge effectively in a complex and unpredictable domain. The thesis argues that an important part of this domain knowledge should be represented in the form of decomposition rules that decompose tasks into subgoals. The thesis presents HOPPER, an implemented planning system that uses decomposition rules and a least-commitment decomposition strategy that strikes a balance between reactive and deliberative planning. Like reactive planners, HOPPER is able to robustly handle and recover from unexpected events with minimal disruption to its plan. Like deliberative planners, it is also able to plan ahead to take advantage of opportunities to interleave and shorten its sub-plans. The thesis also presents TADPOLE, an implemented learning system that learns both the structure and preconditions of new decomposition rules from a small number of lessons demonstrated by a teacher. It learns by parsing and interpreting the teacher’s behaviour in terms of decomposition rules it already knows. It extends its rule set by filling in the holes in its parses of the teacher’s lessons.</b></p> <p>Both HOPPER and TADPOLE have been evaluated together in two different domains: a kitchen domain that emphasizes complexity, and a logistics domain that emphasizes plan efficiency. Every rule used by HOPPER was learned by TADPOLE and every rule learned by TADPOLE was successfully used by HOPPER to achieve various tasks, showing that TADPOLE is able to learn effective decomposition rules from minimal lessons from a teacher, and that HOPPER is able to robustly make use of them even in the face of unexpected events.</p>

Intelligent Agents for E-Learning

2011 ◽  
pp. 25-42
Author(s):  
Ralf Bruns ◽  
Jürgen Dunkel
Keyword(s):  
Web Sites ◽  
Intelligent Agents ◽  
Domain Knowledge ◽  
Multi Agent Systems ◽  
Semantic Web Technologies ◽  
Private Data ◽  
Intelligent Software Agents ◽  
E Learning ◽  
The One ◽  
New Generation

We propose the software architecture of a new generation of advisory systems using Intelligent Agent and Semantic Web technologies. Multi-agent systems provide a well-suited paradigm to implement negotiation processes in consultancy situations. Intelligent software agents act as clients and advisors using their knowledge in order to assist human users. In the proposed architecture the domain knowledge is semantically modeled by means of XML-based ontology languages such as OWL. Using an inference engine the agents reason on base of their knowledge to make decisions or proposals. The agent knowledge consists of different types of data: on the one hand private data, which has to be protected against unauthorized access, and on the other hand publicly accessible data spread over different web sites. Comparable to a real consultancy situation, an agent only reveals sensitive private data if it is indispensable for finding a solution. In addition, depending on the actual consultancy situation each agent dynamically expands its knowledge base by accessing OWL knowledge sources from the Internet. The usefulness of our approach is proved by the implementation of an advisory system whose objective is to develop virtual student advisers that render support to university students in order to successfully organize und perform their studies.

Incremental Ontology Population and Enrichment through Semantic-based Text Mining

2015 ◽  
Vol 11 (3) ◽  
pp. 44-66 ◽  
Author(s):  
Saira Gillani ◽  
Andrea Ko
Keyword(s):  
Text Mining ◽  
Domain Knowledge ◽  
Learning System ◽  
Domain Specific ◽  
Automatic Categorization ◽  
New Concepts ◽  
Domain Specific Knowledge ◽  
E Learning ◽  
Ontology Population ◽  
It Audit

Higher education and professional trainings often apply innovative e-learning systems, where ontologies are used for structuring domain knowledge. To provide up-to-date knowledge for the students, ontology has to be maintained regularly. It is especially true for IT audit and security domain, because technology is changing fast. However manual ontology population and enrichment is a complex task that require professional experience involving a lot of efforts. The authors' paper deals with the challenges and possible solutions for semi-automatic ontology enrichment and population. ProMine has two main contributions; one is the semantic-based text mining approach for automatically identifying domain-specific knowledge elements; the other is the automatic categorization of these extracted knowledge elements by using Wiktionary. ProMine ontology enrichment solution was applied in IT audit domain of an e-learning system. After ten cycles of the application ProMine, the number of automatically identified new concepts are tripled and ProMine categorized new concepts with high precision and recall.

MULTI‐LAYERED KNOWLEDGE‐BASED ARCHITECTURE OF THE ADAPTABLE DISTANCE LEARNING SYSTEM

2009 ◽  
Vol 15 (2) ◽  
pp. 229-244 ◽  
Author(s):  
Dalė Dzemydienė ◽  
Lina Tankelevičienė
Keyword(s):  
Distance Learning ◽  
Intelligent Agents ◽  
Research Work ◽  
Learning System ◽  
Conceptual Approach ◽  
Knowledge Based ◽  
Distance Learning System ◽  
Learning System Architecture ◽  
Service Oriented ◽  
E Learning

The quality of the distance learning courses is largely influenced by competently prepared educational resources and an effective study support system. One of the possible ways to improve distance learning infrastructure and increase its effectiveness is to extend the architecture of present e‐learning systems by the components for adaptable and sustainable learning. This research work is devoted to developing the service‐oriented distance learning environment adaptable to the user's needs. The proposed adaptable communication environment of distance learning is constructed by integration of new components of communication scenarios generation, adaptable for student's goals, multilayered domain ontology of learning subject and forming intelligent agents’ framework possible. The paper presents the knowledge‐based component architecture of the distance learning system, which enables a better adaptation of learning resources to students. The paper analyses the possibilities of integrating ontology into the e‐learning system. The issues of decomposing ontology into different levels of understanding are discussed in order to adapt to learner's tasks and goals. A conceptual approach is proposed for extending the existing distance learning system architecture by intelligent and deeper knowledge layers. Santrauka Nuotolinių studijų kokybė daugiausia priklauso nuo kompetentingai parengtų mokomųjų priemonių ir veiksmingai veikiančios studijų paramos sistemos. Ieškant priemonių, kaip pagerinti nuotolinių studijų sistemos infrastruktūrą ir padidinti jos darbo efektyvumą, nagrinėjamos galimybės praplėsti tradicinės nuotolinio mokymo sistemos architektūrą komponentėmis, kurios leistų išplėtoti adaptuotą ir darnų mokymosi procesą. Šio tyrimo uždaviniai skirti paslaugoms, skirtoms išvystyti nuotolinio mokymo aplinką. Siekiant sukurti tinkamą kompiuterizuotą bendradarbiavimo aplinką, lanksčiai prisitaikoma prie kintančių vartotojo poreikių studijų procese. Architektūra projektuojama integruojant naujas komponentes bendravimo scenarijams generuoti, daugelio lygių dalykinės srities ontologijai naudoti ir sudarant sąlygas automatizuotam intelektinių agentų bendravimui. Straipsnyje nagrinėjamos galimybės integruoti dalykinės srities ontologiją į tradicinės nuotolinio mokymo sistemos aplinką. Ontologijos detalizavimo pagal studento supratimo lygmenis klausimai nagrinėjami siekiant pateikti koncepcinį tokios nuotolinės adaptuotos sistemos darbo modelį.

scholarly journals Attitudes and Perceptions of Students to Open and Distance Learning in Nigeria

2006 ◽  
Vol 7 (1) ◽  
Author(s):  
David Olugbenga Ojo ◽  
Felix Kayode Olakulehin
Keyword(s):  
Higher Education ◽  
Distance Learning ◽  
Teaching And Learning ◽  
Single Mode ◽  
Learning System ◽  
Distance Teaching ◽  
African Region ◽  
Attitudes And Perceptions ◽  
The Face ◽  
Open And Distance Learning

In the West African Region of Africa, the National Open University of Nigeria (NOUN) is the first full fledged university that operates in an exclusively open and distance learning (ODL) mode of education. NOUN focuses mainly on open and distance teaching and learning system, and delivers its courses materials via print in conjunction with information and communication technology (ICT), when applicable. This 'single mode' of open education is different from the integration of distance learning system into the face- to- face teaching and learning system, which is more typical of conventional Universities in Nigeria and other parts of the world. Thus, NOUN reflects a novel development in the provision of higher education in Nigeria. This study assesses the attitudes and perceptions of distance teaching and learning by students enrolled in the NOUN and of the National Teachers' Institute (NTI) compared to their experiences at conventional universities. One hundred and twenty (n = 120) randomly selected NOUN and NTI students of NOUN were the subjects of the study. The Students' Attitude and Perception Rating of Open and Distance Learning Institutions Inventory (SAPRODLII), developed by the researchers, was administered to the subjects to measure their attitudes and experiences. Results of the study showed that students generally have a positive perception and attitude towards ODL, compared to traditional forms of higher education.

Constructing Impossible Uprisings

2017 ◽  
Author(s):  
Frédéric Volpi
Keyword(s):  
Local Level ◽  
Unintended Consequences ◽  
Political Life ◽  
North African ◽  
African Countries ◽  
Unexpected Events ◽  
Causal Processes ◽  
The Face ◽  
North African Countries

This chapter introduces the ‘eventful sociology’ that characterizes the emergence of protest episodes in the four North African countries. Events are non-routine sequences of actions that reshape the routine forms of governance (and opposition) structuring everyday social and political life. Transformative events initiate a transformation of behaviors that is both strategic and reactive, and that reshapes social and political life first at the local level. This chapter qualifies the emergence of new causal processes and how they interact with preexisting practices of governance. The narrative places side by side the views and strategies of different pro- and anti-regime actors in the face of unexpected events and their consequences. The chapter outlines how sequences of events produced new practices, arenas and actors of contestations, often as unintended consequences of interactions. This event-centric account of protest episodes highlights the transformative role of protest in the construction of newly effective forms of political behaviors.

MACE: Mobile Artificial Conversational Entity for Adapting Domain Knowledge and Generating Personalized Advice

2019 ◽  
Vol 28 (04) ◽  
pp. 1940005 ◽  
Author(s):  
Christos Troussas ◽  
Akrivi Krouska ◽  
Maria Virvou
Keyword(s):  
Mobile Learning ◽  
Domain Knowledge ◽  
English Language ◽  
Learning Experience ◽  
New Technology ◽  
Language Instruction ◽  
Educational Process ◽  
Learning System ◽  
Handheld Devices ◽  
Design Development

Mobile learning offers, with the help of handheld devices, a continuous access to the learning process. With the advent of mobile learning, educational systems are changing, offering the possibility of distance education without the restrictions of place and time. As such, new technological advancements are employed by mobile learning. This paper presents the design, development and evaluation of a novel artificial conversational entity, incorporated in a mobile learning system for personalized English language instruction. More specifically, it offers amelioration of the domain knowledge model by adapting it to the students’ needs and to the pace that they prefer to receive learning. Moreover, it creates personalized tutoring advice in order to support students in the educational process. Finally, it can assist the procedure of assessments since it automatically generates questions to assess the knowledge level of students. The evaluation of the mobile tutoring system presents promising results regarding the incorporation of this new technology in digital education with the aim of creating a student-centric learning experience.

Teaching the Ethics/Technology Interface

1987 ◽  
Vol 3 (1) ◽  
pp. 61-66
Author(s):  
Albert R. Jonsen
Keyword(s):  
Electronic System ◽  
Human Experience ◽  
Human Being ◽  
Human Face ◽  
Old World ◽  
New Words ◽  
The Face ◽  
Human World ◽  
The Mind ◽  
The Way

The problem that I will discuss in this essay is marvellously illustrated in the title given to me by the editors. The word “interface” is itself part of the jargon of technology, the technospeak needed by those who develop, use, and discuss functions, things, and relationships that had not existed previously in the human world. They must make up new words to describe new realities (and, unfortunately, allow new and ugly words to obscure old ones). An “interface” presumably describes the way in which one electronic system contacts another so that the first energizes the second. In the old world of human experience, an “interface” is impossible. The face of one human being is visible to another; two faces, smiling or frowning at each other, communicate. The mind behind one face can interpret the movements of another. Never does one human face interpenetrate or merge with another.

Sign in / Sign up

Export Citation Format

Share Document