Conceptualizing procedural knowledge is one of the most challenging tasks of building systems for intelligent tutoring. We presented a novel algorithm for semi-automated conceptualization of procedural knowledge based on goal-oriented rules in symbolic domains. We applied the algorithm to the challenging KBNK chess endgame, and carried out a pilot experiment to evaluate whether the obtained concepts (instructions) could serve as a teaching tool. Somewhat surprisingly, even the beginner-level chess players were able to quickly grasp the concepts, and learn to deliver checkmate. A separate, subjective evaluation of the instructions by experienced chess trainers was also positive.
COBISS.SI-ID: 9326164
The paper presents an important part of the development of a neurological decision support system to help the neurologists differentiate between different types of tremors. The system is intended to act as a second opinion for the neurologists, and most importantly to help them reduce the number of patients in the »gray area« that require a very costly further examination (DaTSCAN). The paper demonstrates advantages of argument-based machine learning in combining effectively machine learning and expert knowledge. The accuracy of the system is very high with respect to the current state-of-the-art in clinical practice, and the obtained system's knowledge base is assessed to be very consistent from a medical point of view. This opens up the possibility to use the system also as a teaching tool.
COBISS.SI-ID: 30199257
We described in detail mechanisms of the ABML knowledge refinement loop, which is a part of argument-based machine learning. The ABML loop draws the expert’s attention to the most critical parts of the current knowledge base, and helps the expert to argue about critical concrete cases in terms of the expert’s own understanding of such cases. Knowledge elicited through ABML refinement loop is therefore more consistent with expert’s knowledge and thus leads to more comprehensible models in comparison with other ways of knowledge acquisition with machine learning from examples. We provided quantitative results that demonstrate how the model evolving through the ABML loop becomes increasingly more consistent with the expert’s knowledge during the process.
COBISS.SI-ID: 9596500