This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fea...
Abdel-rahman Mohamed, Tara N. Sainath, George Dahl...
In applications such as character recognition, some classes are heavily overlapped but are not necessarily to be separated. For classification of such overlapping classes, either d...
We propose a general method for reranker construction which targets choosing the candidate with the least expected loss, rather than the most probable candidate. Different approac...
Despite all the progress in neural networks the technology is still brittle and sometimes difficult to apply. Automatic construction of networks and proper initialization of their...