Communications of the ACM
Machine Learning
Machine Learning
Theoretical Computer Science - Special issue: Algorithmic learning theory
Positivism against constructivism: a network game to learn epistemology
DS'07 Proceedings of the 10th international conference on Discovery science
Assisting scientific discovery with an adaptive problem solver
DS'05 Proceedings of the 8th international conference on Discovery Science
| Hi-index | 0.01 |
Since its inception, the field of machine learning has seen the advent of several learning paradigms, designed to frame the issues central to the learning activity, provide effective learning methods, and investigate the power and limitations inherent to the process of successful learning. In this article, we propose a formalization that underlies the key concepts of many such paradigms and discuss their relevance to scientific discovery, with the aim of assessing what scientists can expect from machines designed to assist them in their quest for the discovery of valid laws. We illustrate the formalization on several variations of a card game, and highlight the differences that paradigms impose on learners, as well as the assumptions they make on the nature of the learning process. We then use the formalization to describe a multi-agent interaction protocol, that has been inspired by these paradigms and that has been validated recently on some groups of agents. Finally, we propose extensions to this protocol.