Faced with an increasing gap between fast growth of data and limited human ability to comprehend data, data analytics tools are now in high demand in many applications across a broad set of domains. In particular, for interactive data exploration systems, an "explore-by-example" framework, which aims to assist the user in performing highly effective data exploration while minimizing the human effort, is becoming increasingly popular. However, the state-of-the-art explore-by-example systems still require a large number of labeled examples to achieve the desired accuracy and cannot handle noisy labels. To address both the slow convergence problem and the label noise problem, in this thesis, we cast the explore-by-example problem in a principl...
Why do people of different linguistic background sometimes perceive the same acoustic signal differe...
Nowadays, more and more data of different kinds is becoming available. Various datasets contain valu...
Molecular docking is a method that predicts orientation of one molecule with respect to another one ...
Source estimation and localization are a central problem in array signal processing, and in particul...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
Accurate egomotion estimation is of utmost importance for any navigation system.Nowadays di_erent se...
Prognostics & Health Management (PHM) aims at extending the life cycle of an engineering asset, whil...
Molecular docking is a method that predicts orientation of one molecule with respect to another one ...
Domains such as medicine, the WWW, business or nance generate and store on a daily basis massive amo...
Cloud federations can be seen as major progress in cloud computing, in particular in the medical dom...
The solution of sparse systems of linear equations is at the heart of numerous applicationfields. Wh...
In the modern era of on-demand ubiquitous computing, where applications and services are deployed in...
Over the past few years, neural network (NN) architectures have been successfully applied to many Na...
Even if they are uncommon, Rare Diseases (RDs) are numerous and generally sever, what makes their st...
In the modern era of on-demand ubiquitous computing, where applications and services are deployed in...
Why do people of different linguistic background sometimes perceive the same acoustic signal differe...
Nowadays, more and more data of different kinds is becoming available. Various datasets contain valu...
Molecular docking is a method that predicts orientation of one molecule with respect to another one ...
Source estimation and localization are a central problem in array signal processing, and in particul...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
Accurate egomotion estimation is of utmost importance for any navigation system.Nowadays di_erent se...
Prognostics & Health Management (PHM) aims at extending the life cycle of an engineering asset, whil...
Molecular docking is a method that predicts orientation of one molecule with respect to another one ...
Domains such as medicine, the WWW, business or nance generate and store on a daily basis massive amo...
Cloud federations can be seen as major progress in cloud computing, in particular in the medical dom...
The solution of sparse systems of linear equations is at the heart of numerous applicationfields. Wh...
In the modern era of on-demand ubiquitous computing, where applications and services are deployed in...
Over the past few years, neural network (NN) architectures have been successfully applied to many Na...
Even if they are uncommon, Rare Diseases (RDs) are numerous and generally sever, what makes their st...
In the modern era of on-demand ubiquitous computing, where applications and services are deployed in...
Why do people of different linguistic background sometimes perceive the same acoustic signal differe...
Nowadays, more and more data of different kinds is becoming available. Various datasets contain valu...
Molecular docking is a method that predicts orientation of one molecule with respect to another one ...