Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, we have to handle small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many acquisition func...

Beyond Deep Learning: Scalable Methods and Models for Learning

The function space of deep-learning machines is investigated by studying growth in the entropy of functions of a given error with respect to a reference function, realized by a deep-learning machine. Using physics-inspired methods we study both sparsely and densely-connected architectures to discover a layer-wise convergence of candidate functions, marked by a corresponding reduction in entropy...

Electronic portfolios (e-portfolios) are a paradigm in constructivist e-learning. They are capable of involving students in deep learning while serving as a meaningful way for both students and faculty to engage in outcomes-based assessment. E-portfolios have been shown to be a valid way to document student progress, encourage greater student involvement in the learning process, showcase work s...

We describe our system in 2014 LifeCLEF [1] Plant Identification Competition. The sub-system for isolated leaf category (LeafScans) was basically the same as last year [2], while plant photographs in all the remaining categories were classified using either local descriptors or deep learning techniques. However, due to large amount of data, large number of classes and shortage of time, our syst...

Mood and emotion although used interchangeably, mood is significantly different from emotion in many aspects. It reflects the internal state of a person compared to a rather transient affective state shown by emotional expressions. Mood inference from voice can provide better performance, however, hardly any study exists that predicts mood from voice. In this paper, we propose a solution to thi...

......................................................................................................................... 3 1 Introduction ............................................................................................................. 3 1.1 Application Background ............................................................................... 4 1.2 Performance Demands for Deep L...