Optimization plays a costly and crucial role in developing machine learn...
Encoder-decoder networks with attention have proven to be a powerful way...
Learned optimizers are increasingly effective, with performance exceedin...
Learned optimizers are algorithms that can themselves be trained to solv...
Despite the widespread application of recurrent neural networks (RNNs) a...
Much as replacing hand-designed features with learned functions has
revo...
Neural networks have a remarkable capacity for contextual processing–usi...
We present TaskSet, a dataset of tasks for use in training and evaluatin...
Recently, deep feedforward neural networks have achieved considerable su...
Task-based modeling with recurrent neural networks (RNNs) has emerged as...
Recurrent neural networks (RNNs) are a widely used tool for modeling
seq...
State-of-the art vision models can achieve superhuman performance on ima...
Deep learning has shown that learned functions can dramatically outperfo...
Deep learning has shown that learned functions can dramatically outperfo...
Many applications in machine learning require optimizing a function whos...
A major goal of unsupervised learning is to discover data representation...
State-of-the-art systems for semantic image segmentation utilize feed-fo...
Learning to learn has emerged as an important direction for achieving
ar...
A central challenge in neuroscience is to understand neural computations...
A central problem in machine learning involves modeling complex data-set...