We study the problem of learning using combinations of machines. In particular we present new theoretical bounds on the generalization performance of voting ensembles of kernel ma...
We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resul...
Michael Karlen, Jason Weston, Ayse Erkan, Ronan Co...
We present a new method for transductive learning, which can be seen as a transductive version of the k nearest-neighbor classifier. Unlike for many other transductive learning me...
Abstract. The protein family classification problem, which consists of determining the family memberships of given unknown protein sequences, is very important for a biologist for ...
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...