This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...

this study aims to better understand the effect of practice schedule and feedback providing types. in two separate experiments the contextual interference effect in bandwidth and self-control feedback conditions on relative and absolute timing learning was examined. in experiment i, the effect of contextual interference using bandwidth and self-control feedback on absolute timing learning (para...

Objectives: The current study mainly aimed at studying the effect of Knowledge of Result (KR) feedback timing and result-estimation opportunity before receiving delayed KR on learning a new speech motor skill in monolingual healthy adults.  Methods: Thirty-nine Persian healthy adults were randomly divided into three groups. Each group received immediate KR, delayed KR (after eight seconds), or...

In order to identify the dimensions and indices of the phenomenon of “leading transfer of learning” within the secondary schools of Tehran province, a sample of 17 lecturers, principals, and experienced teachers was targeted and then interviewed. Inductive analyses of the collected data at three levels of open, pivotal, and selective coding indicate that the role of high school principals along...

This commentary argues that to fully appreciate the complexities of knowledge transfer one firstly has to distinguish between the notions of “data, information, knowledge and wisdom,” and that the latter two are highly context sensitive. In particular one has to understand knowledge as being personal rather than objective, and hence there is no form of knowledge that a-priori is more authoritat...

In transfer learning, we wish to make inference about a target population when have access data both from the distribution itself, and different but related source distribution. We introduce flexible framework for learning in context of binary classification, allowing covariate-dependent relationships between distributions that are not required preserve Bayes decision boundary. Our main contrib...

Transfer learning aims to provide a framework to utilize previously-acquired knowledge to solve new but similar problems much more quickly and effectively. In contrast to classical machine learning methods, transfer learning methods exploit the knowledge accumulated from data in auxiliary domains to facilitate predictive modeling consisting of different data patterns in the current domain. To i...