We present a method for mapping a given Bayesian network to a Boltzmann machine architecture, in the sense that the the updating process of the resulting Boltzmann machine model pr...
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
Hugo Larochelle, Dumitru Erhan, Aaron C. Courville...
The space of bio-inspired hardware can be partitioned along three axes: phylogeny, ontogeny, and epigenesis. We refer to this as the POE model. Our Embryonics (for embryonic electr...
The self-organizing map SOM is widely used as a data visualization method in various engineering applications. It performs a non-linear mapping from a high-dimensional data spac...
Abstract. In our previous work we have shown that Mahalanobis kernels are useful for support vector classifiers both from generalization ability and model selection speed. In this ...