Institution
Company•Tel Aviv, Israel•
About: Facebook is a company organization based out in Tel Aviv, Israel. It is known for research contribution in the topics: Artificial neural network & Language model. The organization has 7856 authors who have published 10906 publications receiving 570123 citations. The organization is also known as: facebook.com & FB.
Topics: Artificial neural network, Language model, Reinforcement learning, Machine translation, Social network
Papers published on a yearly basis
Papers
More filters
•
01 Jan 2020TL;DR: One of the earliest commonly-used packages is Spearmint, which implements a variety of modeling techniques such as MCMC hyperparameter sampling and input warping.
Abstract: Bayesian optimization provides sample-efficient global optimization for a broad range of applications, including automatic machine learning, engineering, physics, and experimental design. We introduce BoTorch, a modern programming framework for Bayesian optimization that combines Monte-Carlo (MC) acquisition functions, a novel sample average approximation optimization approach, auto-differentiation, and variance reduction techniques. BoTorch's modular design facilitates flexible specification and optimization of probabilistic models written in PyTorch, simplifying implementation of new acquisition functions. Our approach is backed by novel theoretical convergence results and made practical by a distinctive algorithmic foundation that leverages fast predictive distributions, hardware acceleration, and deterministic optimization. We also propose a novel "one-shot" formulation of the Knowledge Gradient, enabled by a combination of our theoretical and software contributions. In experiments, we demonstrate the improved sample efficiency of BoTorch relative to other popular libraries.
307 citations
•
16 May 2001TL;DR: In this article, the authors propose a wireless communication system for digital audio players that provides for increased functionality, such as communication, interaction and synchronization between a computing platform and various mobile, portable or fixed DAs, as well as providing a communication link between the DAs themselves.
Abstract: A wireless communication system and in particular to a wireless communication system for digital audio players that provides for increased functionality, such as communication, interaction and synchronization between a computing platform and various mobile, portable or fixed digital audio players, as well as providing a communication link between the various digital audio players themselves. The computing platform may act, for example, through a wireless network or wireless communication platform, to control the digital audio players; to act as a cache of digital audio data for the digital audio players; as well as provide a gateway to the Internet to enable the digital audio players to access additional digital audio content and other information. The computing platform may also be used to automatically update digital audio content on the digital audio players; synchronize digital audio content and playlists between digital audio players; and automatically continue a particular playlist as the user moves from one digital audio player to another.
306 citations
•
TL;DR: The proposed CNN-RNN framework learns a joint image-label embedding to characterize the semantic label dependency as well as the image- label relevance, and it can be trained end-to-end from scratch to integrate both information in a unified framework.
Abstract: While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels, which could correspond to different objects, scenes, actions and attributes in an image. Traditional approaches to multi-label image classification learn independent classifiers for each category and employ ranking or thresholding on the classification results. These techniques, although working well, fail to explicitly exploit the label dependencies in an image. In this paper, we utilize recurrent neural networks (RNNs) to address this problem. Combined with CNNs, the proposed CNN-RNN framework learns a joint image-label embedding to characterize the semantic label dependency as well as the image-label relevance, and it can be trained end-to-end from scratch to integrate both information in a unified framework. Experimental results on public benchmark datasets demonstrate that the proposed architecture achieves better performance than the state-of-the-art multi-label classification model
305 citations
•
06 Oct 2009TL;DR: In this article, a method and/or system allows a user of a social networking service to publish a content item tagged with location information for sharing with other users of the social network service.
Abstract: A method and/or system allows a user of a social networking service to publish a content item tagged with location information for sharing with other users of the social networking service. The user publishing the content item performs operations on the originating device to generate the content item. The originating communication device attaches the location information to the content item, and transmits the content item to a social networking system. The social networking system may provide various location-based services based on the content item tagged with the location information.
305 citations
•
TL;DR: Feature denoising networks as mentioned in this paper uses non-local means or other filters to denoise the features of CNNs and achieve state-of-the-art performance in both white-box and black-box attacks.
Abstract: Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks. Motivated by this observation, we develop new network architectures that increase adversarial robustness by performing feature denoising. Specifically, our networks contain blocks that denoise the features using non-local means or other filters; the entire networks are trained end-to-end. When combined with adversarial training, our feature denoising networks substantially improve the state-of-the-art in adversarial robustness in both white-box and black-box attack settings. On ImageNet, under 10-iteration PGD white-box attacks where prior art has 27.9% accuracy, our method achieves 55.7%; even under extreme 2000-iteration PGD white-box attacks, our method secures 42.6% accuracy. Our method was ranked first in Competition on Adversarial Attacks and Defenses (CAAD) 2018 --- it achieved 50.6% classification accuracy on a secret, ImageNet-like test dataset against 48 unknown attackers, surpassing the runner-up approach by ~10%. Code is available at this https URL.
302 citations
Authors
Showing all 7875 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yoshua Bengio | 202 | 1033 | 420313 |
Xiang Zhang | 154 | 1733 | 117576 |
Jitendra Malik | 151 | 493 | 165087 |
Trevor Darrell | 148 | 678 | 181113 |
Christopher D. Manning | 138 | 499 | 147595 |
Robert W. Heath | 128 | 1049 | 73171 |
Pieter Abbeel | 126 | 589 | 70911 |
Yann LeCun | 121 | 369 | 171211 |
Li Fei-Fei | 120 | 420 | 145574 |
Jon Kleinberg | 117 | 444 | 87865 |
Sergey Levine | 115 | 652 | 59769 |
Richard Szeliski | 113 | 359 | 72019 |
Sanjeev Kumar | 113 | 1325 | 54386 |
Bruce Neal | 108 | 561 | 87213 |
Larry S. Davis | 107 | 693 | 49714 |