Filter by Research Area
Filter by Research Area
Year Published

550 Results

July 9, 2018

Mixed batches and symmetric discriminators for GAN training

International Conference on Machine Learning (ICML)

We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch.

By: Thomas Lucas, Corentin Tallec, Jakob Verbeek, Yann Ollivier
July 9, 2018

Composable Planning with Attributes

International Conference on Machine Learning (ICML)

We propose a method that learns a policy for transitioning between “nearby” sets of attributes, and maintains a graph of possible transitions.

By: Amy Zhang, Adam Lerer, Sainbayar Sukhbaatar, Rob Fergus, Arthur Szlam
July 7, 2018

Reconstructing Scenes with Mirror and Glass Surfaces

ACM SIGGRAPH

We introduce a fully automatic pipeline that allows us to reconstruct the geometry and extent of planar glass and mirror surfaces while being able to distinguish between the two.

By: Thomas Whelan, Michael Goesele, Steven J. Lovegrove, Julian Straub, Simon Green, Richard Szeliski, Steven Butterfield, Shobhit Verma, Richard Newcombe
July 7, 2018

Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations

arXiv

We show that the gradient descent algorithm provides an implicit regularization effect in the learning of over-parameterized matrix factorization models and one-hidden-layer neural networks with quadratic activations.

By: Yuanzhi Li, Tengyu Ma, Hongyang Zhang
July 1, 2018

We Need a Testability Transformation Semantics

16th International Conference on Software Engineering and Formal Methods

This paper briefly reviews Testability Transformation, its formal definition, and the open problem of constructing a set of formal test adequacy semantics to underpin the current practice of deploying transformations to help testing and verification activities.

By: Mark Harman
June 29, 2018

Understanding the Loss Surface of Neural Networks for Binary Classification

International Conference on Machine Learning (ICML)

Here we focus on the training performance of neural networks for binary classification, and provide conditions under which the training error is zero at all local minima of appropriately chosen surrogate loss functions.

By: Shiyu Liang, Ruoyu Sun, Yixuan Li, R. Srikant
June 28, 2018

Hardware Remediation At Scale

International Conference on Dependable Systems and Networks (DSN)

Large scale services have automated hardware remediation to maintain the infrastructure availability at a healthy level. In this paper, we share the current remediation flow at Facebook, and how it is being monitored.

By: Fan (Fred) Lin, Matt Beadon, Harish Dattatraya Dixit, Gautham Vunnam, Amol Desai, Sriram Sankar
June 25, 2018

HALE Multidisciplinary Design Optimization Part II: Solar-Powered Flying-Wing Aircraft

AIAA Aviation

In this paper (Part II), we describe how a solar-powered flying-wing configuration may be optimized using a strategy similar to that described in Part I.

By: Dorian F. Colas, Nicholas H. Roberts, Vishvas S. Suryakumar
June 25, 2018

Solar Aircraft Design Trade Studies Using Geometric Programming

AIAA Aviation

Solar aircraft design is a multidisciplinary problem in which tradeoffs between aerodynamic performance, structural integrity, component performance, cost, and manufacturability are complex and non-intuitive.

By: Michael Burton, Christopher Courtin, Mark Drela, Dorian Colas, Nicholas Roberts, Vishvas Suryakumar
June 25, 2018

“I’m Never Happy with What I Write”: Challenges and Strategies of People with Dyslexia on Social Media

International Conference on Web and Social Media

This work studies the experiences, challenges, and strategies of people with dyslexia when using social media. We interviewed 11 people with dyslexia to understand their general experiences with reading and writing content on Facebook. The interview study findings highlight the challenges they face when writing content on Social Networking Sites (SNSs), and their strategies for mitigating these challenges.

By: Lindsay Reynolds, Shaomei Wu