This work examines the challenges of training neural networks using vect...
Recent advances in deep learning, in particular enabled by hardware adva...
We present a generic method for recurrently using the same parameters fo...
Modern deep neural networks are highly over-parameterized compared to th...
Reinforcement learning (RL) in real-world safety-critical target setting...
Co-occurrence statistics based word embedding techniques have proved to ...
We present a method for storing multiple models within a single set of
p...
A major goal of unsupervised learning is to discover data representation...
Recent work has shown that recurrent neural networks can be trained to
s...
Recent work has shown that recurrent neural networks can be trained to
s...
Machine learning models are vulnerable to adversarial examples: small ch...
We describe a neural attention model with a learnable retinal sampling
l...
Deep learning has enjoyed a great deal of success because of its ability...
We present an efficient algorithm for simultaneously training sparse
gen...