In this paper, we present a robust feature extraction framework based on informationtheoretic learning. Its formulated objective aims at simultaneously maximizing the Renyi's...
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...
This paper proposes a pedagogical framework for informal language learning services via interactive television. We argue that mapping current language learning theories onto learn...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
Term-based representations of documents have found widespread use in information retrieval. However, one of the main shortcomings of such methods is that they largely disregard le...