For many practical learning scenarios, the integrated use of more than one learning tool is educationally beneficial. In these cases, interoperability between learning tools – getting the pieces to talk – is a crucial requirement that is often hard to achieve. This paper describes an architecture that aims at the integration of independent learning tools into one collaborative learning scenario.

Nowadays, advanced E-Learning systems are generally pedagogy-aware. Commonly, these systems include facilities for defining so-called learning scenarios that reflect sophisticated pedagogical approaches such as collaborative writing or project-oriented learning. To support different learning activities from such scenarios the technological infrastructure of these systems must be appropriately a...

Probabilistic classification and multi-task learning are two important branches of machine learning research. Probabilistic classification is useful when the ‘confidence’ of decision is necessary. On the other hand, the idea of multi-task learning is beneficial if multiple related learning tasks exist. So far, kernelized logistic regression has been a vital probabilistic classifier for the use ...

E-Learning is increasingly influencing university and workplace education in Europe. The EU/IST FP6 Network of Excellence PROLEARN is focussing on these issues, advancing the state of the art in this area. Some of PROLEARNs key issues are the production, deployment, exchange and brokerage of learning resources as well as their usage for professional training in SMEs and larger companies. Furthe...

In this paper, a novel approach proposed for structural damage detection from limited number of sensors using extreme learning machine (ELM). As the number of sensors used to measure modal data is normally limited and usually are less than the number of DOFs in the finite element model, the model reduction approach should be used to match with incomplete measured mode shapes. The second-order a...

One of the main promoted advantages deep learning in profiling sidechannel analysis is possibility skipping feature engineering process. Despite that, most recent publications consider selection as attacked interval from side-channel measurements pre-selected. This similar to worst-case security assumptions evaluations when random secret shares (e.g., mask shares) are known during phase: an eva...

Reinforcement learning (RL) is a biologically supported learning paradigm, which allows an agent to learn through experience acquired by interaction with its environment. Its potential to learn complex action sequences has been proven for a variety of problems, such as navigation tasks. However, the interactive randomized exploration of the state space, common in reinforcement learning, makes i...

A number of studies have evidenced that handheld devices are appropriate tools to facilitate face-to-face collaborative learning effectively because of the possibility of ample social interactions. Group Area Network, or GroupNet, proposed in this paper, uses handheld devices to fill the gap between Local Area Network and Body Area Network. GroupNet is an independent network where all members a...

Numerous groups have applied a variety of deep learning techniques to computer vision problems in highway perception scenarios. In this paper, we presented a number of empirical evaluations of recent deep learning advances. Computer vision, combined with deep learning, has the potential to bring about a relatively inexpensive, robust solution to autonomous driving. To prepare deep learning for ...