Owing to the tremendous increase in the volume and variety of user generated content, train–once– apply–forever models are insufficient for supervised learning tasks. Thus, developing algorithms that adapt across domains by leveraging data from multiple domains is critical. However, existing adaptation algorithms often fail to identify the right sources to use for adaptation. In this work, we p...

Classical dynamins bind the plasma membrane-localized phosphatidylinositol-4,5-bisphosphate using the pleckstrin-homology domain (PHD) and engage in rapid membrane fission during synaptic vesicle recycling. This domain is conspicuously absent among extant bacterial and mitochondrial dynamins, however, where loop regions manage membrane recruitment. Inspired by the core design of bacterial and m...

Information is central to healthcare: for proper care, information must be shared. Modern healthcare is highly collaborative, involving interactions between users from a range of institutions, including primary and secondary care providers, researchers, government and private organisations. Each has specific data requirements relating to the service they provide, and must be informed of relevan...

We extend the Structural Correspondence Learning (SCL) domain adaptation algorithm of Blitzer et al. [4] to the realm of continuous signals. Given a set of labeled examples belonging to a “source” domain, we select a set of unlabeled examples in a related “target” domain that play similar roles in both domains. Using these “pivot samples,” we map both domains into a common feature space, allowi...

in the present paper, we introduce the sequence space [{l_p}(e,delta) = left{ x = (x_n)_{n = 1}^infty : sum_{n = 1}^infty left|  sum_{j in {e_n}} x_j - sum_{j in e_{n + 1}} x_jright| ^p < infty right},] where $e=(e_n)$ is a partition of finite subsets of the positive integers and $pge 1$. we investigate its topological properties and inclusion relations. moreover, we consider the problem of fin...

Transfer learning algorithms can be used when sufficient amount of training data is available in the source domain and limited training data is available in the target domain. The transfer of knowledge from one domain to another requires similarity between two domains. In many resource-poor languages, it is rare to find labeled training data in both the source and target domains. Active learnin...

Topic models can be used in an unsupervised domain adaptation for Word Sense Disambiguation (WSD). In the domain adaptation task, three types of topic models are available: (1) a topic model constructed from the source domain corpus: (2) a topic model constructed from the target domain corpus, and (3) a topic model constructed from both domains. Basically, three topic features made from each to...

In this paper we report the contribution of XRCE team to the Domain Adaptation Challenge [10] organized in the framework of ImageCLEF 2014 competition [9]. We describe our approach to build an image classification system when a weak image annotation in the target domain is compensated by massively annotated images in source domains. One method is based using several heterogeneous methods for th...