Loading...
Projects / Programmes source: ARIS

Machine learning for building intelligent tutoring systems

Research activity

Code Science Field Subfield
2.07.07  Engineering sciences and technologies  Computer science and informatics  Intelligent systems - software 

Code Science Field
P170  Natural sciences and mathematics  Computer science, numerical analysis, systems, control 

Code Science Field
1.02  Natural Sciences  Computer and information sciences 
Keywords
artificial intelligence, intelligent tutoring systems, machine learning
Evaluation (rules)
source: COBISS
Researchers (9)
no. Code Name and surname Research area Role Period No. of publicationsNo. of publications
1.  02275  PhD Ivan Bratko  Computer science and informatics  Head  2011 - 2014  743 
2.  28365  PhD Matej Guid  Computer science and informatics  Researcher  2011 - 2014  88 
3.  14075  PhD Alenka Horvat Ledinek  Neurobiology  Researcher  2011 - 2014  137 
4.  29021  PhD Martin Možina  Computer science and informatics  Researcher  2011 - 2014  77 
5.  05380  PhD Zvezdan Pirtošek  Neurobiology  Researcher  2011 - 2014  748 
6.  15441  PhD Uroš Rot  Neurobiology  Researcher  2011 - 2014  185 
7.  20389  PhD Aleksander Sadikov  Computer science and informatics  Researcher  2011 - 2014  191 
8.  08752  PhD Saša Šega Jazbec  Cardiovascular system  Researcher  2011 - 2014  200 
9.  29020  PhD Jure Žabkar  Computer science and informatics  Researcher  2011 - 2014  129 
Organisations (2)
no. Code Research organisation City Registration number No. of publicationsNo. of publications
1.  0312  University Medical Centre Ljubljana  Ljubljana  5057272000  77,744 
2.  1539  University of Ljubljana, Faculty of Computer and Information Science  Ljubljana  1627023  16,285 
Abstract
Project summary   It is generally accepted that one-to-one tutoring is by far more effective than in-class teaching, but too costly in most situations. To carry out one-to-one tutoring at reasonable cost, CAI (Computer Assisted Instruction) is an alternative. To overcome CAI’s rigid behaviour, ITS (Intelligent Tutoring Systems) are generally considered as the most promising option. However, the costs of ITS development are high because it requires major involvement of a domain expert to realise intelligent student-system interaction. The purpose of this project is to develop methods for automating the process of developing ITS and thus considerably decrease the high costs of building ITS, by enabling more economical, semi-automatic development of  ITS. In particular, the main goals of the project is to develop methods to support automated conceptualisation of learning domains, which can be viewed as a key component in the construction of ITS systems. In the project, several experimental case studies in selected learning domains will be carried out from two types of domains: symbolic problem solving, like physics, medical reasoning and chess, and motor and/or control skill domains like running, walking in parients, or tennis. The role of domain conceptualisation is as follows. In complex domains, the connection between the basic domain theory (axioms, laws, formulas, rules of the game, etc.) and problem solutions is usually rather complex and hard for a human to execute. Therefore, there is typically a need for an intermediate theory, conceptualised domain theory,  that serves as a bridge between the basic declarative domain theory and procedural knowledge for concrete problem solving. This can be viewed in terms of a derivation chain as follows. Basic domain theory (axioms, etc.) logically entails a  “conceptualised domain theory”, which in turn entails problem solutions. Logically, the basic domain theory also entails problems solutions, but at much higher problem-solving effort. The basic theory is typically “non-operational” for a human (requires excessive computation, or it may be too complex to memorise), whereas the conceptualised theory is “human-assimilable”. These relations can be illustrated as follows:   original theory ---------------------------------------) problem solution original theory  ----)  conceptualised theory ---) problem solution   A conceptualised domain is a problem solving tool for a human, and therefore it should be simple and compact, so that it can be understood, memorised, and executed in problem solving by the student.  The planned conceptualisation methods will be based on some recent methods and paradigms of AI which will be adapted and further elaborated for the purpose of this project. These techniques and paradigms include: ABML (Argument Based Machine Learning) , QR (Qualitative Reasoning and modelling) , Q2 learning (Qualitatively faithful Quantitative learning), EBG and EBL (Explanation Based Generalisation and Learning), ILP (Inductive Logic Programming), and specific techniques of behavioural cloning (capturing human skill from observed human’s behaviours). The developed conceptualisation methods will be experimentally applied to intelligent tutoring systems for selected domains as follows: (1) symbolic problem-solving domains: physics, medical diagnostic reasoning (diagnosis of tremors), and chess; (2) motor skill domains: running, tennis, walking in patients (multiple sclerosis)   The AI part of the project will be carried out by the Artificial Intelligence Laboratory of Univ. of Ljubljana, and LMG laboratory of the Ljubljana Clinical Centre will collaborate in the neurological medical applications. These medical applications are expected to be directly adopted in the medical practice.
Significance for science
Main scientific contributions of the project are in the area of building intelligent tutoring systems with AI techniques. Most notably, to the problem of conceptualisation of problem domains. That is, how to transform a given basic declarative theory (stated as axioms, laws, formulas, rules of the game) that is not suitable for efficient problem solving, into an operational, conceptualised theory that can be used effectively for problem solving by a student. We developed some novel approaches to estimating problem-solving skills and estimating the difficulty of problems for a human. We also created foundations of automated assessment of difficulty of problems for humans.
Significance for the country
The project is important with respect to the training of postgraduate and undergraduate students in the fast-evolving area of artificial intelligence in education. Direct application of developed software will be possible in teaching computer programming. The application for diagnosing tremors, developed in this project, is important for direct application in medicine. It is generally available as a mobile application ParkinsonCheck.
Most important scientific results Annual report 2011, 2012, 2013, final report, complete report on dLib.si
Most important socioeconomically and culturally relevant results Annual report 2011, 2012, 2013, final report, complete report on dLib.si
Views history
Favourite