scispace - formally typeset
Search or ask a question
Institution

Amazon.com

CompanySeattle, Washington, United States
About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Service (business) & Service provider. The organization has 13363 authors who have published 17317 publications receiving 266589 citations.


Papers
More filters
Journal ArticleDOI
Philip M. Fearnside1
TL;DR: In this article, the authors consider conversion to a landscape of agriculture, productive pasture, degraded pasture, secondary forest, and regenerated forest in the proportions corresponding to the equilibrium condition implied by current land-use patterns.
Abstract: Deforestation in Brazilian Amazonia is a significant source of greenhouse gases today and, with almost 90% of the originally forested area still uncleared, is a very large potential source of future emissions. The 1990 rate of loss of forest (13.8 × 103 km2/year) and cerrado savanna (approximately 5 × 103 km2/year) was responsible for releasing approximately 261 × 106 metric tons of carbon (106 t C) in the form of CO2, or 274–285 × 106 t of CO2-equivalent C considering IPCC 1994 global warming potentials for trace gases over a 100-year horizon. These calculations consider conversion to a landscape of agriculture, productive pasture, degraded pasture, secondary forest, and regenerated forest in the proportions corresponding to the equilibrium condition implied by current land-use patterns. Emissions are expressed as ‘net committed emissions’, or the gases released over a period of years as the carbon stock in each hectare deforested approaches a new equilibrium in the landscape that replaces the original forest. For low and high trace gas scenarios, respectively, 1990 clearing produced net committed emissions (in 106 t of gas) of 957–958 for CO2, 1.10–1.42 for CH4, 28–35 for CO, 0.06–0.16 for N2O, 0.74–0.74 for NOx and 0.58–1.16 for non-methane hydrocarbons.

302 citations

Posted Content
Tong He1, Zhi Zhang1, Hang Zhang1, Zhongyue Zhang1, Junyuan Xie1, Mu Li1 
TL;DR: This paper examines a collection of training procedure refinements and empirically evaluates their impact on the final model accuracy through ablation study, and shows that by combining these refinements together, they are able to improve various CNN models significantly.
Abstract: Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either briefly mentioned as implementation details or only visible in source code. In this paper, we will examine a collection of such refinements and empirically evaluate their impact on the final model accuracy through ablation study. We will show that, by combining these refinements together, we are able to improve various CNN models significantly. For example, we raise ResNet-50's top-1 validation accuracy from 75.3% to 79.29% on ImageNet. We will also demonstrate that improvement on image classification accuracy leads to better transfer learning performance in other application domains such as object detection and semantic segmentation.

299 citations

Proceedings ArticleDOI
Sungsoo Ahn1, Shell Xu Hu, Andreas Damianou2, Neil D. Lawrence2, Zhenwen Dai2 
15 Jun 2019
TL;DR: In this article, the authors propose an information-theoretic framework for knowledge transfer which formulates knowledge transfer as maximizing the mutual information between the teacher and the student networks, and compare their method with existing knowledge transfer methods on both knowledge distillation and transfer learning tasks and show that their method consistently outperforms existing methods.
Abstract: Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student neural network. Existing knowledge transfer approaches match the activations or the corresponding hand-crafted features of the teacher and the student networks. We propose an information-theoretic framework for knowledge transfer which formulates knowledge transfer as maximizing the mutual information between the teacher and the student networks. We compare our method with existing knowledge transfer methods on both knowledge distillation and transfer learning tasks and show that our method consistently outperforms existing methods. We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10. The resulting MLP significantly outperforms the-state-of-the-art methods and it achieves similar performance to the CNN with a single convolutional layer.

298 citations

Patent
10 Jun 2004
TL;DR: In this article, the authors describe a web site system that persistently stores event data reflective of events that occur during browsing sessions of web site users, and makes such data available to other applications and services in real time.
Abstract: A web site system (30) includes an event history server system (32) that persistently stores event data reflective of events that occur during browsing sessions of web site users, and makes such data available to other applications and services (38) in real time. The server system (32) may, for example, be used to record information about every mouse click of every recognized user, and may also be used to record other types of events such as impressions and mouse-over events. The event data of a particular user may be retrieved from the server system (32) based on event type, event time of occurrence, and various other criteria. In one embodiment, the server system (32) includes a cache layer (40) that caches event data by session ID, and includes a persistent storage layer (44) that persistently stores the event data by user ID. Also disclosed are various application features that may be implemented using the stored event data.

293 citations

Journal ArticleDOI
Philip M. Fearnside1
TL;DR: In this article, the authors present an unweighted mean basic density of 0.65 (range 0.14-1.21) for 268 species of trees in the Amazonian forests.

291 citations


Authors

Showing all 13498 results

NameH-indexPapersCitations
Jiawei Han1681233143427
Bernhard Schölkopf1481092149492
Christos Faloutsos12778977746
Alexander J. Smola122434110222
Rama Chellappa120103162865
William F. Laurance11847056464
Andrew McCallum11347278240
Michael J. Black11242951810
David Heckerman10948362668
Larry S. Davis10769349714
Chris M. Wood10279543076
Pietro Perona10241494870
Guido W. Imbens9735264430
W. Bruce Croft9742639918
Chunhua Shen9368137468
Network Information
Related Institutions (5)
Microsoft
86.9K papers, 4.1M citations

89% related

Google
39.8K papers, 2.1M citations

88% related

Carnegie Mellon University
104.3K papers, 5.9M citations

87% related

ETH Zurich
122.4K papers, 5.1M citations

82% related

University of Maryland, College Park
155.9K papers, 7.2M citations

82% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
20234
2022168
20212,015
20202,596
20192,002
20181,189