7k citations
- University of California, Santa BarbaraUS99 papers
- University of California, BerkeleyUS35 papers
- ETH ZurichCH32 papers
- University of Maryland, College ParkUS29 papers
- California Institute of TechnologyUS25 papers
- Stanford UniversityUS25 papers
- Microsoft Research (United Kingdom)GB23 papers
- Princeton UniversityUS20 papers
- Cornell UniversityUS19 papers
- University of WashingtonUS17 papers
- University of California, Los AngelesUS16 papers
- Massachusetts Institute of TechnologyUS13 papers
80 papers · 1 filter
On Enriching the Levin-Wen model with Symmetry
Liang Chang, Meng Cheng, Shawn X. Cui +6
Symmetry protected and symmetry enriched topological phases of matter are of great interest in condensed matter physics due to new materials such as topological insulators. The Lev…
Whoo.ly: Facilitating Information Seeking For Hyperlocal Communities Using Social Media
Yuheng Hu, Shelly D. Farnham, Andres Monroy-Hernandez
Social media systems promise powerful opportunities for people to connect to timely, relevant information at the hyper local level. Yet, finding the meaningful signal in noisy soci…
Declaratively solving tricky Google Code Jam problems with Prolog-based ECLiPSe CLP system
Sergii Dymchenko, Mariia Mykhailova
In this paper we demonstrate several examples of solving challenging algorithmic problems from the Google Code Jam programming contest with the Prolog-based ECLiPSe system using de…
Convolutional Neural Networks at Constrained Time Cost
Kaiming He, Jian Sun
Though recent advanced convolutional neural networks (CNNs) have been improving the image recognition accuracy, the models are getting more complex and time-consuming. For real-wor…
Competing with the Empirical Risk Minimizer in a Single Pass
Roy Frostig, Rong Ge, Sham M. Kakade +1
In many estimation problems, e.g. linear and logistic regression, we wish to minimize an unknown objective given only unbiased samples of the objective function. Furthermore, we ai…
Training Deep Neural Networks on Noisy Labels with Bootstrapping
Scott Reed, Honglak Lee, Dragomir Anguelov +3
Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting.…