We review the application of statistical mechanics methods to the study of online learning of a drifting concept in the limit of large systems. The model where a feed-forward netwo...
Execution paths expose non-functional information such as system reliability and performance, which can be collected using runtime verification techniques. Statistics gathering an...
Factored Statistical Machine Translation extends the Phrase Based SMT model by allowing each word to be a vector of factors. Experiments have shown effectiveness of many factors, ...
We study how the choice of packet scheduling algorithms influences end-to-end performance on long network paths. Taking a network calculus approach, we consider both deterministi...
: Multilingual natural language processing systems are increasingly relying on parallel corpus to ameliorate their output. Parallel corpora constitute the basic block for training ...