We present a novel language identification technique using our recently developed deep-structured conditional random fields (CRFs). The deep-structured CRF is a multi-layer CRF mo...
Probabilistic language models are critical to applications in natural language processing that include speech recognition, optical character recognition, and interfaces for text e...
Sparse matrices are first class objects in many VHLLs (very high level languages) used for scientific computing. They are a basic building block for various numerical and combinat...
Learning function relations or understanding structures of data lying in manifolds embedded in huge dimensional Euclidean spaces is an important topic in learning theory. In this ...
In many sensor networking environments, the sensor nodes have limited battery capacity and processing power. Hence, it is imperative to develop solutions that are energy-efficient...