We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
We organized a challenge for IJCNN 2007 to assess the added value of prior domain knowledge in machine learning. Most commercial data mining programs accept data pre-formatted in ...
Isabelle Guyon, Amir Saffari, Gideon Dror, Gavin C...
We propose a novel, computationally efficient generative topographic model for inferring low dimensional representations of high dimensional data sets, designed to exploit data s...
Object detection remains an important but challenging task in computer vision. We present a method that combines high accuracy with high efficiency. We adopt simplified forms of...
Signal modeling lies at the core of numerous signal and image processing applications. A recent approach that has drawn considerable attention is sparse representation modeling, in...