• Publications
  • Influence
Automatic differentiation in PyTorch
TLDR
In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models. Expand
  • 6,929
  • 844
PyTorch: An Imperative Style, High-Performance Deep Learning Library
TLDR
This paper introduces PyTorch, a Python library that performs immediate execution of dynamic tensor computations with automatic differentiation and GPU acceleration, and does so while maintaining performance comparable to the fastest current libraries for deep learning. Expand
  • 2,659
  • 313
  • PDF
Tabulator: Exploring and Analyzing linked data on the Semantic Web
TLDR
The Tabulator is an RDF browser, which is designed both for new users to provoke interest in the Semantic Web and give them a means to access and interact with the entire web of RDF data. Expand
  • 483
  • 44
  • PDF
Open data kit: tools to build information services for developing regions
TLDR
This paper presents Open Data Kit (ODK), an extensible, open-source suite of tools designed to build information services that can both push and pull information in developing regions. Expand
  • 393
  • 35
  • PDF
Learning Physical Intuition of Block Towers by Example
TLDR
This paper makes the following contributions: Convnet-based Prediction models successfully generalize in two important ways: (i) to new physical scenarios, e.g. towers with an additional block and (ii) to images of real wooden blocks. Expand
  • 208
  • 19
  • PDF
A MultiPath Network for Object Detection
TLDR
The recent COCO object detection dataset presents several new challenges for object detection. Expand
  • 156
  • 17
  • PDF
Open Source Data Collection in the Developing World
TLDR
The ability to collect data is key to the success of many organizations operating in the developing world. Expand
  • 121
  • 17
Deep Counterfactual Regret Minimization
TLDR
This paper introduces Deep Counterfactual Regret Minimization, a form of CFR that obviates the need for abstraction by instead using deep neural networks to approximate the behavior of CFR in the full game. Expand
  • 48
  • 17
  • PDF
PyTorch-BigGraph: A Large-scale Graph Embedding System
TLDR
We present PyTorch-BigGraph (PBG), an embedding system that incorporates several modifications to traditional multi-relation embedding systems that allow it to scale to graphs with billions of nodes and trillions of edges. Expand
  • 80
  • 13
  • PDF
Maintaining cooperation in complex social dilemmas using deep reinforcement learning
TLDR
We show how to modify modern reinforcement learning methods to construct agents that act in ways that are simple to understand, nice (begin by cooperating), provokable ( try to avoid being exploited), and forgiving (try to return to mutual cooperation). Expand
  • 68
  • 6
  • PDF