Machine Learning
We argue that, when establishing and benchmarking Machine Learning (ML) models, the research community should favour evaluation metrics …
In many applications, it is desirable to extract only the relevant information from complex input data, which involves making a …
Recent advances have made it possible to create deep complex-valued neural networks. Despite this progress, the potential power of …
We present Hinted Networks: a collection of architectural transformations for improving the accuracies of neural network models for …
The Probably Approximately Correct (PAC) Bayes framework (McAllester, 1999) can incorporate knowledge about the learning algorithm and …
Despite the advances in the representational capacity of approximate distributions for variational inference, the optimization process …
Learning long-term dependencies in extended temporal sequences requires credit assignment to events far back in the past. The most …
At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations …
The recent literature on deep learning offers new tools to learn a rich probability distribution over high dimensional data such as …
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it …