Many approaches to learning classifiers for structured objects (e.g., shapes) use generative models in a Bayesian framework. However, state-of-the-art classifiers for vectorial d...
Abstract—Natural language understanding involves the simultaneous consideration of a large number of different sources of information. Traditional methods employed in language an...
Efficiently managing storage is important for virtualized computing environments. Its importance is magnified by developments such as cloud computing which consolidate many thousa...
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Kernel methods have been shown to be very effective for applications requiring the modeling of structured objects. However kernels for structures usually are too computational dem...
Fabio Aiolli, Giovanni Da San Martino, Alessandro ...