In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have be...
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...
Social and emotional intelligence are aspects of human intelligence that have been argued to be better predictors than IQ for measuring aspects of success in life, especially in s...
Maja Pantic, Nicu Sebe, Jeffrey F. Cohn, Thomas S....
We present a new technique that employs support vector machines and Gaussian mixture densities to create a generative/discriminative joint classifier. In the past, several approac...
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....