In this paper the design and development approach of an authoring tool for defining pedagogical relationship types is described. Pedagogical relationship types are used to define adaptation strategies which can be used by an adaptation engine to create an adaptive course based on user model information. Based on domain models consisting of concepts and relationships between concepts, pedagogica...

The predicted manifestations of global climate change are diverse and extensive. Information and Communications Technologies (ICTs) offer great potential to enable and enhance climate change adaptation projects, programmes and activities. As yet these roles have received relatively little systematic consideration. In this paper we outline the nature of climate change adaptation contexts and pre...

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain c...

We learn multiple hypotheses for related tasks under a latent hierarchical relationship between tasks. We exploit the intuition that for domain adaptation, we wish to share classifier structure, but for multitask learning, we wish to share covariance structure. Our hierarchical model is seen to subsume several previously proposed multitask learning models and performs well on three distinct rea...

We introduce a hierarchical statistical language model, represented as a collection of local models plus a general sentence model. We provide an example that mixes a trigram general model and a PFSA local model for the class of decimal numbers, described in terms of sub-word units (graphemes). This model practically extends the vocabulary of the overall model to an infinite size, but still has ...

The problem of information searching is very common in the age internet and Big Data. Usually, there are huge collections documents only multiple percent them relevant. In this setup brute-force methods useless. Search engines help to solve optimally. Most based on learning rank methods, i.e. first all algorithm produce scores for they feature after that sorts according score an appropriate ord...

In recent years, impressive advances have been made in single-image super-resolution. Deep learning is behind much of this success. Deep(er) architecture design and external prior modeling are the key ingredients. The internal contents low-resolution input image neglected with deep modeling, despite earlier works that show power using such priors. paper, we propose a variation residual convolut...