Genome-wide microarray designs containing millions to hundreds of millions of probes are available for a variety of mammals, including mouse and human. These genome tiling arrays ...
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...
We propose a computer-aided methodology to automatically generate time optimal production schemes for chemical batch plants operating in multi-batch mode. Our approach is based on ...
: Computational classification of proteins using methods such as string kernels and Fisher-SVM has demonstrated great success. However, the resulting models do not offer an immedia...
We propose a sequential Monte Carlo data association algorithm based on a two-level computational framework for tracking varying number of interacting objects in dynamic scene. Fi...