We propose online prediction algorithms for data streams whose characteristics might change over time. Our algorithms are applications of online learning with experts. In particular, our algorithms combine base predictors over sliding windows with different length as experts. As a result, our algorithms are guaranteed to be competitive with the base predictor with the best fixed-length sliding ...

Federated learning (FL) is an emerging distributed machine paradigm that avoids data sharing among training nodes so as to protect privacy. Under the coordination of FL server, each client conducts model using its own computing resource and private set. The global can be created by aggregating results clients. To cope with highly non-IID distributions, personalized federated (PFL) has been prop...

We consider a budgeted variant of the problem of learning from expert advice with N experts. Each queried expert incurs a cost and there is a given budget B on the total cost of experts that can be queried in any prediction round. We provide an online learning algorithm for this setting with regret after T prediction rounds bounded by

Deep learning methods are the de facto solutions to a multitude of medical image analysis tasks. Cardiac MRI segmentation is one such application, which, like many others, requires large number annotated data so that trained network can generalize well. Unfortunately, process having manually curated images by experts both slow and utterly expensive. In this paper, we set out explore whether exp...

Unsupervised learning algorithms can discover models of student behavior without any initial work by domain experts, but they also tend to produce complicated, uninterpretable models that may not predict student learning. We propose a simple, unsupervised clustering algorithm for hidden Markov models that can discover student learning tactics while incorporating student-level outcome data, cons...

Exploiting experts' knowledge can significantly increase the quality of Bayesian network (BN) structures produced by learning algorithms. However, in practice, experts may not be 100% confident about opinions they provide. Worst, latter also conflicting. Including such specific algorithms is therefore complex. In literature, there exist a few score-based that exploit both data and existence/abs...

Learning Bayesian network structures from data is known to be hard, mainly because the number of candidate graphs is super-exponential in the number of variables. Furthermore, using observational data alone, the true causal graph is not discernible from other graphs that model the same set of conditional independencies. In this paper, it is investigated whether Bayesian network structure learni...

e-Learning has some restrictions on how learning performance is assessed. Online testing is usually in the form of multiple-choice questions, without any essay type of learning assessment. Major reasons for employing multiple-choice tasks in e-learning include ease of implementation and ease of managing learner's responses. To address this limitation in online assessment of learning, this study...

In our knowledge society learning is a very important and broad topic that includes several unsolved questions. Among them the transfer of novices into experts remains elusive. The paper shows that the cognitive elements and mental models needed for the expert execution of a task or skill can be used in cooperation with suitable exercises and intelligent elearning systems to obtain a faster and...