A core challenge in the interpretation of deep neural networks is identi...
Neuroscience has long been an important driver of progress in artificial...
Recurrent neural networks (RNNs) are powerful models for processing
time...
Learned optimizers are algorithms that can themselves be trained to solv...
Despite the widespread application of recurrent neural networks (RNNs) a...
Neural networks have a remarkable capacity for contextual processing–usi...
Task-based modeling with recurrent neural networks (RNNs) has emerged as...
Recurrent neural networks (RNNs) are a widely used tool for modeling
seq...
Feed-forward convolutional neural networks (CNNs) are currently
state-of...
A vexing problem in artificial intelligence is reasoning about events th...
State-of-the-art systems for semantic image segmentation utilize feed-fo...
Two potential bottlenecks on the expressiveness of recurrent neural netw...
There exist many problem domains where the interpretability of neural ne...
A major hurdle to clinical translation of brain-machine interfaces (BMIs...
Neuroscience is experiencing a data revolution in which many hundreds or...
Sequence-to-sequence models have achieved impressive results on various
...
Training very deep networks is an important open problem in machine lear...