检索结果-内蒙古大学图书馆

arXiv 2022年

作者： McNeely, Trey Khokhlov, Pavel Dalmasso, Niccolò Wood, Kimberly M. Lee, Ann B. Carnegie Mellon University Department of Statistics and Data Science United States J.P. Morgan AI Research Mississippi State University Department of Geosciences United States Microsoft AI Development Acceleration Program

Because geostationary satellite (Geo) imagery provides a high temporal resolution window into tropical cyclone (TC) behavior, we investigate the viability of its application to short-term probabilistic forecasts of TC convective structure to subsequently predict TC intensity. Here, we present a prototype model which is trained solely on two inputs: Geo infrared imagery leading up to the synoptic time of interest and intensity estimates up to 6 hours prior to that time. To estimate future TC structure, we compute cloud-top temperature radial profiles from infrared imagery and then simulate the evolution of an ensemble of those profiles over the subsequent 12 hours by applying a Deep Autoregressive Generative Model (PixelSNaiL). To forecast TC intensities at hours 6 and 12, we input operational intensity estimates up to the current time (0 h) and simulated future radial profiles up to +12 h into a "nowcasting" convolutional neural network. We limit our inputs to demonstrate the viability of our approach and to enable quantification of value added by the observed and simulated future radial profiles beyond operational intensity estimates alone. Our prototype model achieves a marginally higher error than the National Hurricane Center's official forecasts despite excluding environmental factors, such as vertical wind shear and sea surface temperature. We also demonstrate that it is possible to reasonably predict short-term evolution of TC convective structure via radial profiles from Geo infrared imagery, resulting in interpretable structural forecasts that may be valuable for TC operational guidance. © 2022, CC BY.

关键词： Geostationary satellites

来源：评论

学校读者我要写书评

暂无评论

Differentially private synthetic data: Applied evaluations and enhancements

arXiv

引用

arXiv 2020年

作者： Rosenblatt, Lucas Liu, Xiaoyan Pouyanfar, Samira de Leon, Eduardo Desai, Anuj Allen, Joshua Microsoft United States Microsoft AI Development and Acceleration Program United States

Machine learning practitioners frequently seek to leverage the most informative available data, without violating the data owner’s privacy, when building predictive models. Differentially private data synthesis protects personal details from exposure, and allows for the training of differentially private machine learning models on privately generated datasets. But how can we effectively assess the efficacy of differentially private synthetic data? In this paper, we survey four differentially private generative adversarial networks for data synthesis. We evaluate each of them at scale on five standard tabular datasets, and in two applied industry scenarios. We benchmark with novel metrics from recent literature and other standard machine learning tools. Our results suggest some synthesizers are more applicable for different privacy budgets, and we further demonstrate complicating domain-based tradeoffs in selecting an approach. We offer experimental learning on applied machine learning scenarios with private internal data to researchers and practioners alike. In addition, we propose QUaiL, an ensemble-based modeling approach to generating synthetic data. We examine QUaiL’s tradeoffs, and note circumstances in which it outperforms baseline differentially private supervised learning models under the same budget constraint. © 2020, CC-BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Human-ai Alignment: Emerging Challenges and Opportunities

Bidirectional Human-AI Alignment: Emerging Challenges and Op...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Shen, Hua Knearem, Tiffany Ghosh, Reshmi Liu, Michael Xieyang Monroy-Hernández, Andrés Wu, Tongshuang Yang, Diyi Huang, Yun Mitra, Tanushree Li, Yang Hearst, Marti The Information School University of Washington SeattleWA United States Google San FranciscoCA United States Microsoft Corp Microsoft AI Development Acceleration Program CambridgeMA United States Google DeepMind PittsburghPA United States Princeton University PrincetonNJ United States Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Computer Science Department Stanford University StanfordCA United States School of Information Sciences University of Illinois at Urbana-Champaign ChampaignIL United States University of Washington SeattleWA United States Google Research Mountain ViewCA United States UC Berkeley BerkeleyCA United States

ISBN: (纸本)9798400713958

Recent advancements in general-purpose ai have highlighted the urgent need to align ai systems with the goals, ethical principles, and values of individuals and society. Existing alignment research has been primarily approached as an ai-centered, static, and unidirectional process. However, this unidirectional perspective falls short of taking into account the dynamic and evolving interaction between humans and ai, necessitating a shift toward a bidirectional, interconnected mode of human-ai alignment. This SIG aims to outline the emerging areas of bidirectinoal human-ai alignment research, propose a blueprint of future goals and challenges for fundamental alignment research, and establish a shared platform to bring together experts from HCI, ai, social sciences, and more to advance interdisciplinary research and collaboration on human-ai alignment. © 2025 Copyright held by the owner/author(s).

关键词： Sociology

来源：评论

学校读者我要写书评

暂无评论

ML-Assisted Monitoring and Characterization of IoT Sensor Networks

ML-Assisted Monitoring and Characterization of IoT Sensor Ne...

引用

IEEE Workshop on Evolving and Adaptive Intelligent Systems (EaiS)

作者： Karine Ip Abhijith Asok Yijia Xu Duc Le Natalie Mionis Roman Batoukov Soundararajan Srinivasan Microsoft AI Development Acceleration Program Microsoft Cambridge MA USA Azure IoT TSI RnD Microsoft Redmond WA USA

ISBN: (数字)9781728143842

ISBN: (纸本)9781728143859

IoT (Internet of Things) is a dynamic and evolving paradigm with a huge potential for applications across a variety of domains. The number of IoT sensors and volume of telemetry data is growing exponentially, while human capacity to analyze the data remains constant. Hence, current domain applications will benefit from ML-powered solutions that focus human attention on contextually relevant telemetry signals, and automatically infer non-trivial relationships between sensors within a network to assist engineers in troubleshooting complex systems faster. This paper proposes a machine-learning pipeline to characterize a system that is being monitored by an IoT sensor network via a three-pronged approach: monitoring, support diagnostics, ontology augmentation. The pipeline uses an adaptive anomaly detector and applies a novel multi-step, topologically-formulated clustering method on the detected sensor anomalies. It also utilizes an automated pattern mining engine to surface nontrivial sensor relationships based on historic clustering results to augment the static topology of the sensor network. We also provide an illustrative case study in the domain of smart building to showcase the potential application of our pipeline in aiding HVAC maintenance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Black is to criminal as caucasian is to police: Detecting and removing multiclass bias inword embeddings

arXiv

引用

arXiv 2019年

作者： Manziniy, Thomas Limz, Yao Chong Tsvetkovz, Yulia Blackz, Alan W. Microsoft AI Development Acceleration Program Carnegie Mellon University

Online texts-across genres, registers, domains, and styles-are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, we propose a method to debias word embeddings in multiclass settings such as race and religion, extending the work of (Bolukbasi et al., 2016) from the binary setting, such as binary gender. Next, we propose a novel methodology for the evaluation of multiclass debiasing. We demonstrate that our multiclass debiasing is robust and maintains the efficacy in standard NLP tasks. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

MMLSpark: Unifying machine learning ecosystems at massive scales

arXiv

引用

arXiv 2018年

作者： Hamilton, Mark Raghunathan, Sudarshan Matiach, Ilya Schonhoffer, Andrew Raman, Anand Barzilay, Eli Rajendran, Karthik Banda, Dalitso Hong, Casey Jisoo Knoertzer, Manon Brodsky, Ben Thigpen, Minsoo Mahajan, Janhavi Suresh Cochrane, Courtney Eswaran, Abhiram Green, Ari Microsoft Applied AI CambridgeMA United States Microsoft Applied AI RedmondWA United States Microsoft Azure Machine Learning CambridgeMA United States Microsoft AI Development Acceleration Program CambridgeMA United States

We introduce microsoft Machine Learning for Apache Spark (MMLSpark), an open-source library that expands the Apache Spark distributed computing library to tackle problems in deep learning, micro-service orchestration, gradient boosting, model interpretability, and other areas of modern machine learning. We also present a novel machine learning deployment system called Spark Serving that can deploy Apache Spark programs as distributed, sub-millisecond latency web services with significantly greater flexibility and lower latencies than existing frameworks. Spark Serving generalizes beyond just map-style computations and allows distributed aggregations, joins, and shuffles and allows users to leverage the same cluster for both training and deployment. Our contributions allow easy composition across machine learning frameworks, compute modes (batch, streaming, and RESTful web serving) and cluster types (static, elastic, and serverless). We demonstrate the value of MMLSpark by creating a method for deep object detection capable of learning without human labeled data and demonstrate its effectiveness for Snow Leopard conservation. We also demonstrate its ability to create large-scale image search engines. Copyright © 2018, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：