Data augmentation methods have played an important role in the recent ad...
This paper introduces JaxPruner, an open-source JAX-based pruning and sp...
Deep networks have achieved impressive results on a range of well-curate...
While deep learning has been very beneficial in data-rich settings, task...
Identifying the locations and footprints of buildings is vital for many
...
The softmax function combined with a cross-entropy loss is a principled
...
Sparse Neural Networks (NNs) can match the generalization of dense NNs u...
Memorization in over-parameterized neural networks could severely hurt
g...
Neural network pruning techniques have demonstrated it is possible to re...
How do we know if communication is emerging in a multi-agent system? The...
Writers generally rely on plans or sketches to write long stories, but m...
We explore story generation: creative systems that can build coherent an...
We introduce Parseval networks, a form of deep neural networks in which ...
The task of the emotion recognition in the wild (EmotiW) Challenge is to...
The contractive auto-encoder learns a representation of the input data t...