Explore chapters and articles related to this topic
Machine learning
Published in Janet Finlay, Alan Dix, An Introduction to Artificial Intelligence, 2020
Even if no non-deductive steps are made, explanation-based learning gives an important boost to deductive learning – it suggests useful things to learn. This is especially true if the explanation is based on a low-level, perhaps physical, model. The process of looking at examples of phenomena and then explaining them can turn this physical knowledge into higher-level heuristics. For example, given the example of someone slipping on ice, an explanation based on physical knowledge could deduce that the pressure of the person melted the ice and that the presence of the resulting thin layer of water allowed the foot to move relative to the ice. An analysis of this explanation would reveal, amongst other things, that thin layers of fluid allow things to move more easily – the principle of lubrication.
Introduction to Expert Systems
Published in Chris Nikolopoulos, Expert Systems, 1997
In explanation based learning, knowledge is derived from a single training instance by explaining why the given instance is an example of the concept to be learned. For an introduction to explanation based learning, see Mitchell et al., ([18]).
Detecting logical argumentation in text via communicative discourse tree
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2018
Boris Galitsky, Dmitry Ilvovsky, Sergey O. Kuznetsov
To measure the similarity of abstract entities that are expressed by logic formulas, a least-general generalisation, or anti-unification, was proposed for a number of machine learning approaches, including explanation-based learning and inductive logic programming. We extend the notion of generalisation from logic formulas to the sets of syntactic parse trees of these portions of text. Rather than extracting common keywords, the generalisation operation produces a syntactic expression that can be semantically interpreted as a common meaning shared by two sentences.