Amazon.com

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.

PacGAN: The power of two samples in generative adversarial networks

Abstract: Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements in generating realistic images, one of their major shortcomings is the fact that in practice, they tend to produce samples with little diversity, even when trained on diverse datasets. This phenomenon, known as mode collapse, has been the main focus of several recent advances in GANs. Yet there is little understanding of why mode collapse happens and why existing approaches are able to mitigate mode collapse. We propose a principled approach to handling mode collapse, which we call packing. The main idea is to modify the discriminator to make decisions based on multiple samples from the same class, either real or artificially generated. We borrow analysis tools from binary hypothesis testing---in particular the seminal result of Blackwell [Bla53]---to prove a fundamental connection between packing and mode collapse. We show that packing naturally penalizes generators with mode collapse, thereby favoring generator distributions with less mode collapse during the training process. Numerical experiments on benchmark datasets suggests that packing provides significant improvements in practice as well.

Threat detection and mitigation through run-time introspection and instrumentation

Abstract: A system and method for threat detection and mitigation through run-time introspection. The system and method comprising receiving a request to monitor a computing environment. Based on the received request, the system and method further includes determining a set of introspection points for monitoring the computing environment. receive a request to monitor a computing environment, measuring at individual introspection points of the set of introspection points to obtain a set of measurements, generating a graph of a set of resources in the computing environment, wherein the graph correlates individual resources in the set of resources to other resources based on at based at least in part on the set of measurements, and determining whether to perform a security action based at least in part on whether an evaluation of the graph indicates a threat to the computing environment.

The 4th AI City Challenge

Abstract: The AI City Challenge was created to accelerate intelligent video analysis that helps make cities smarter and safer. Transportation is one of the largest segments that can benefit from actionable insights derived from data captured by sensors, where computer vision and deep learning have shown promise in achieving large-scale practical deployment. The 4th annual edition of the AI City Challenge has attracted 315 participating teams across 37 countries, who leverage city-scale real traffic data and high-quality synthetic data to compete in four challenge tracks. Track 1 addressed video-based automatic vehicle counting, where the evaluation is conducted on both algorithmic effectiveness and computational efficiency. Track 2 addressed city-scale vehicle re-identification with augmented synthetic data to substantially increase the training set for the task. Track 3 addressed city-scale multi-target multi-camera vehicle tracking. Track 4 addressed traffic anomaly detection. The evaluation system shows two leader boards, in which a general leader board shows all submitted results, and a public leader board shows results limited to our contest participation rules, that teams are not allowed to use external data in their work. The general leader board shows results more close to real-world situations where annotated data are limited. Our results show promise that AI technology can enable smarter and safer transportation systems.

Applicability of machine learning in spam and phishing email filtering: review and approaches

Abstract: With the influx of technological advancements and the increased simplicity in communication, especially through emails, the upsurge in the volume of unsolicited bulk emails (UBEs) has become a severe threat to global security and economy. Spam emails not only waste users’ time, but also consume a lot of network bandwidth, and may also include malware as executable files. Alternatively, phishing emails falsely claim users’ personal information to facilitate identity theft and are comparatively more dangerous. Thus, there is an intrinsic need for the development of more robust and dependable UBE filters that facilitate automatic detection of such emails. There are several countermeasures to spam and phishing, including blacklisting and content-based filtering. However, in addition to content-based features, behavior-based features are well-suited in the detection of UBEs. Machine learning models are being extensively used by leading internet service providers like Yahoo, Gmail, and Outlook, to filter and classify UBEs successfully. There are far too many options to consider, owing to the need to facilitate UBE detection and the recent advances in this domain. In this paper, we aim at elucidating on the way of extracting email content and behavior-based features, what features are appropriate in the detection of UBEs, and the selection of the most discriminating feature set. Furthermore, to accurately handle the menace of UBEs, we facilitate an exhaustive comparative study using several state-of-the-art machine learning algorithms. Our proposed models resulted in an overall accuracy of 99% in the classification of UBEs. The text is accompanied by snippets of Python code, to enable the reader to implement the approaches elucidated in this paper.

Estimating the Impacts of Local Policy Innovation: The Synthetic Control Method Applied to Tropical Deforestation.

Abstract: Quasi-experimental methods increasingly are used to evaluate the impacts of conservation interventions by generating credible estimates of counterfactual baselines. These methods generally require large samples for statistical comparisons, presenting a challenge for evaluating innovative policies implemented within a few pioneering jurisdictions. Single jurisdictions often are studied using comparative methods, which rely on analysts’ selection of best case comparisons. The synthetic control method (SCM) offers one systematic and transparent way to select cases for comparison, from a sizeable pool, by focusing upon similarity in outcomes before the intervention. We explain SCM, then apply it to one local initiative to limit deforestation in the Brazilian Amazon. The municipality of Paragominas launched a multi-pronged local initiative in 2008 to maintain low deforestation while restoring economic production. This was a response to having been placed, due to high deforestation, on a federal “blacklist” that increased enforcement of forest regulations and restricted access to credit and output markets. The local initiative included mapping and monitoring of rural land plus promotion of economic alternatives compatible with low deforestation. The key motivation for the program may have been to reduce the costs of blacklisting. However its stated purpose was to limit deforestation, and thus we apply SCM to estimate what deforestation would have been in a (counterfactual) scenario of no local initiative. We obtain a plausible estimate, in that deforestation patterns before the intervention were similar in Paragominas and the synthetic control, which suggests that after several years, the initiative did lower deforestation (significantly below the synthetic control in 2012). This demonstrates that SCM can yield helpful land-use counterfactuals for single units, with opportunities to integrate local and expert knowledge and to test innovations and permutations on policies that are implemented in just a few locations.