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...
Content-based retrieval and recognition of graphic images requires good models for symbol representation, able to identify those features providing the most relevant information a...
Unsupervised learning can be used to extract image representations that are useful for various and diverse vision tasks. After noticing that most biological vision systems for int...
Recent computational approaches to action imitation have advocated the use of hierarchical representations in the perception and imitation of demonstrated actions. Hierarchical re...
Collecting, organizing, and thinking about diverse information resources is the keystone of meaningful digital information experiences, from research to education to leisure. Meta...
Andruid Kerne, Yin Qu, Andrew M. Webb, Sashikanth ...