This paper considers the Pointer Value Retrieval (PVR) benchmark introdu...
Recent work has uncovered a striking phenomenon in large-capacity neural...
Convolutional neural networks (CNNs) have so far been the de-facto model...
The successes of deep learning critically rely on the ability of neural
...
Effective training of deep neural networks can be challenging, and there...
A key factor in the success of deep neural networks is the ability to sc...
A central challenge in developing versatile machine learning systems is
...
Over the past few years, we have seen fundamental breakthroughs in core
...
An important research direction in machine learning has centered around
...
In a wide array of areas, algorithms are matching and surpassing the
per...
With the increasingly varied applications of deep learning, transfer lea...
Large labeled datasets for supervised learning are frequently constructe...
Comparing different neural network representations and determining how
r...
State of the art computer vision models have been shown to be vulnerable...
Deep reinforcement learning has achieved many recent successes, but our
...
We propose a new technique, Singular Vector Canonical Correlation Analys...
We introduce LAMP: the Linear Additive Markov Process. Transitions in LA...
We survey results on neural network expressivity described in "On the
Ex...
We combine Riemannian geometry with the mean field theory of high dimens...
We propose a new approach to the problem of neural network expressivity,...