This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and ...
Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabha...
Cross-domain learning methods have shown promising
results by leveraging labeled patterns from auxiliary domains
to learn a robust classifier for target domain, which
has a limi...
Dong Xu, Ivor Wai-Hung Tsang, Lixin Duan, Stephen ...
The notion of algorithmic stability has been used effectively in the past to derive tight generalization bounds. A key advantage of these bounds is that they are designed for spec...
Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. In multi-stage Optima...
We describe an efficient learning algorithm for aligning a symbolic representation of a musical piece with its acoustic counterpart. Our method employs a supervised learning appr...