Expressive performance modeling requires different information for each expressive dimension. Most systems, however, rely on a single approach for all dimensions. Further, tempo and timing are mostly treated as one atomic entity instead of being decomposed into elements and treated separately. We propose a performance model that discriminates expressive dimensions with regard to the modeling ap...

Online learning has great potential to provide students with meaningful learning (Anderson, 1996), however online learning like any other form of structured learning requires careful design, management and facilitation. The world of virtual education with its variety of learning environments built on the basis of students remote from any physical classroom, promotes a need to establish systems ...

Few-shot learning refers to understanding new concepts from only a few examples. We propose an information retrieval-inspired approach for this problem that is motivated by the increased importance of maximally leveraging all the available information in this low-data regime. We define a training objective that aims to extract as much information as possible from each training batch by effectiv...

......................................................................................4 Introduction...................................................................................4 Methods.......................................................................................6 Results.......................................................................................11 Discussion............

Performance prediction asks how much time executing an application is likely to take on a particular machine. Machine ranking asks which of a set of machines is likely to execute an application most quickly. These two questions are discussed within the context of large parallel applications run on supercomputers. Different techniques are surveyed, including a framework for a general approach th...

A new theoretical/empirical model has been developed for performance prediction of hard rock TBMs. The model uses information on the rock properties and cutting geometry to calculate TBM rate of penetration. The model can also be used for TBM butterhead design optimization to achieve maximum performance in a given geology.

The results of recent studies on prediction markets are encouraging. Prior experience demonstrates that markets with different incentive schemes predicted uncertain future events at a remarkable accuracy. In this paper, we study the impact of different monetary incentives on the prediction accuracy in a field experiment. In order to do so, we compare three groups of users, corresponding to thre...

i

Demonstrations from a teacher are invaluable to any student trying to learn a given behavior. Used correctly, demonstrations can speed up both human and machine learning by orders of magnitude. An important question, then, is how best to extract the knowledge encoded by the teacher in these demonstrations. In this paper, we present a method of learning from demonstrations that leverages some of...