检索结果-内蒙古大学图书馆

8th International Conference on learning Representations, ICLR 2020

作者： Wang, Hongyi Yurochkin, Mikhail Sun, Yuekai Papailiopoulos, Dimitris Khazaeni, Yasaman Department of Computer Sciences University of Wisconsin-Madison United States IBM Research MIT-IBM Watson AI Lab United States Department of Statistics University of Michigan United States Department of Electrical and Computer Engineering University of Wisconsin-Madison United States

Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud. We propose the Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs. FedMA constructs the shared global model in a layer-wise manner by matching and averaging hidden elements (i.e. channels for convolution layers;hidden states for LSTM;neurons for fully connected layers) with similar feature extraction signatures. Our experiments indicate that FedMA not only outperforms popular state-of-the-art federated learning algorithms on deep CNN and LSTM architectures trained on real world datasets, but also reduces the overall communication burden. © 2020 8th International Conference on learning Representations, ICLR 2020. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Automated Real-Time Roadway Asset Inventory using Artificial Intelligence

引用

TRANSPORTATION RESEARCH RECORD 2020年第11期2674卷 220-234页

作者： Kargah-Ostadi, Nima Waqar, Ammar Hanif, Adil iENGINEERING Chantilly VA 20152 USA

Roadway asset inventory data are essential in making data-driven asset management decisions. Despite significant advances in automated data processing, the current state of the practice is semi-automated. This paper demonstrates integration of the state-of-the-art artificial intelligence technologies within a practical framework for automated real-time identification of traffic signs from roadway images. The framework deploys one of the very latest machine learning algorithms on a cutting-edge plug-and-play device for superior effectiveness, efficiency, and reliability. The proposed platform provides an offline system onboard the survey vehicle, that runs a lightweight and speedy deep neural network on each collected roadway image and identifies traffic signs in real-time. Integration of these advanced technologies minimizes the need for subjective and time-consuming human interventions, thereby enhancing the repeatability and cost-effectiveness of the asset inventory process. The proposed framework is demonstrated using a real-world image dataset. Appropriate pre-processing techniques were employed to alleviate limitations in the training dataset. A deep learning algorithm was trained for detection, classification, and localization of traffic signs from roadway imagery. The success metrics based on this demonstration indicate that the algorithm was effective in identifying traffic signs with high accuracy on a test dataset that was not used for model development. Additionally, the algorithm exhibited this high accuracy consistently among the different considered sign categories. Moreover, the algorithm was repeatable among multiple runs and reproducible across different locations. Above all, the real-time processing capability of the proposed solution reduces the time between data collection and delivery, which enhances the data-driven decision-making process.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

learning the graphical structure of electronic health records with graph convolutional transformer 34

Learning the graphical structure of electronic health record...

引用

34th AAAI Conference on Artificial Intelligence, AAAI 2020

作者： Choi, Edward Xu, Zhen Li, Yujia Dusenberry, Michael W. Flores, Gerardo Xue, Emily Dai, Andrew M. Google Mountain View United States DeepMind London United Kingdom

ISBN: (纸本)9781577358350

Effective modeling of electronic health records (EHR) is rapidly becoming an important topic in both academia and industry. A recent study showed that using the graphical structure underlying EHR data (e.g. relationship between diagnoses and treatments) improves the performance of prediction tasks such as heart failure prediction. However, EHR data do not always contain complete structure information. Moreover, when it comes to claims data, structure information is completely unavailable to begin with. Under such circumstances, can we still do better than just treating EHR data as a flat-structured bag-of-features? In this paper, we study the possibility of jointly learning the hidden structure of EHR while performing supervised prediction tasks on EHR data. Specifically, we discuss that Transformer is a suitable basis model to learn the hidden EHR structure, and propose Graph Convolutional Transformer, which uses data statistics to guide the structure learning process. The proposed model consistently outperformed previous approaches empirically, on both synthetic data and publicly available EHR data, for various prediction tasks such as graph reconstruction and readmission prediction, indicating that it can serve as an effective general-purpose representation learning algorithm for EHR data. Copyright © 2020, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Web Application for Feral Cat Recognition Through Deep learning 9th

A Web Application for Feral Cat Recognition Through Deep Lea...

引用

9th International Conference on Big Data, BigData 2020, held as part of the Services Conference Federation, SCF 2020

作者： Zhou, Jingling Wang, Shiyu Chen, Yunxue Sinnott, Richard O. School of Computing and Information Systems University of Melbourne Melbourne Australia

ISBN: (纸本)9783030596118

Deep learning has gained much attention and been applied in many different fields. In this paper, we present a web application developed to identify and detect the number of distinct feral cats of Australia using deep learning algorithms targeted to data captured from a set of remote sensing cameras. Feral cat recognition is an especially challenging application of deep learning since the cats are often similar and, in some cases, differ only in very small patterns on their fur. Given the automated, sensor-based image capture from remote cameras, further challenges relate to the limited number of images available. To tackle this, we train four neural network models to distinguish 75 classes (i.e. distinct feral cats) using 30 to 80 images for each class. Based on a range of evaluation metrics, we select Mask R-CNN model with ImageNet pre-trained weights augmented with the ResNet-50 network as the basis for the web application. Using images of cats from cameras in five different forests around Victoria, we achieved an average accuracy of identification of individual (distinct) cats of 89.4% with a maximum accuracy of 96.3%. This work is used to support ecologists in the School of Biosciences at the University of Melbourne. © 2020, Springer Nature Switzerland AG.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Why state-of-the-art deep learning barely works as good as a linear classifier in extreme multi-label text classification 28

Why state-of-the-art deep learning barely works as good as a...

引用

28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine learning, ESANN 2020

作者： Qaraei, Mohammadreza Khandagale, Sujay Babbar, Rohit Aalto University CS Department Helsinki Finland Columbia University CS Department New York United States

ISBN: (纸本)9782875870742

Extreme Multi-label Text Classification (XMTC) refers to supervised learning of a classifier which can predict a small subset of relevant labels for a document from an extremely large set. Even though deep learning algorithms have surpassed linear and kernel methods for most natural language processing tasks over the last decade;recent works show that state-of-the-art deep learning methods can only barely manage to work as well as a linear classifier for the XMTC task. The goal of this work is twofold: (i) to investigate the reasons for the comparable performance of these two strands of methods for XMTC, and (ii) to document this observation explicitly, as the efficacy of linear classifiers in this regime, has been ignored in many relevant recent works. © ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine learning.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A deep learning algorithm for detection of potassium deficiency in a red grapevine and spraying actuation using a raspberry pi3

A deep learning algorithm for detection of potassium deficie...

引用

2020 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems, icABCD 2020

作者： Ukacgbu, Uchechi Tartibu, Lagouge Laseinde, Timothy Okwu, Modestus Olayode, Isaac Department of Mechanical and Industrial Engineering University of Johannesburg Johannesburg South Africa

ISBN: (纸本)9781728167701

The fourth industrial revolution (4IR) has ushered in advancement, which is currently reshaping all sectors of the economy. including the agricultural domain. This paper describes the application of artificial intelligence technique on an embedded device. It involves the smart detection of potassium deficiency in red grape vines using the deep learning algorithm. This was deployed on a raspberry pi-3 for real-time actuation and effective prediction. The light-emitting diode (LED) was lit when a potassium deficient red grapevine leaf was brought close to the pi-camera. Image data obtained was fed as input into the model. Training. validation, and testing accuracies of 89%, 81 and 80% were obtained respectively for the CNN model which surpassed the performance of the Support Vector Machines (SVM) classifier. This research has demonstrated a paradigm shift from the conventional agricultural method of detecting nutrient deficiency to a more effective real-time deep learning algorithm which prompt a corresponding actuation to effectively spray of fertilizers. This technique in no doubt would lead to tremendous increase in food production. © 2020 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

DeepSeismic: A deep learning library for seismic interpretation 1

DeepSeismic: A deep learning library for seismic interpretat...

引用

1st EAGE Digitalization Conference and Exhibition

作者： Salvaris, M. Kaznady, M. Paunic, V. Karmanov, I. Bhatia, A. Tok, W.H. Chikkerur, S. Microsoft

We introduce DeepSeismic, an open source Github repository (https://***/microsoft/seismicdeeplearning) that provides implementation of deep learning algorithms for seismic facies interpretation. The repository provides composable machine learning pipelines, that enables a data scientists and geophysicists to use state-of-the-art segmentation algorithms for seismic interpretation (e.g. UNet: Ronneberger et al. (2015), SEResNet:Hu et al. (2018), HRNet: Sun et al. (2019)) . We provide scripts to reproduce benchmark results from running these algorithms using various public seismic datasets (Dutch F3, and Penobscot). Finally,the repository provides documentation, and quick start Jupyter notebook and Python scripts to enable the community to get started with seismic interpretation projects quickly. We believe the results in this paper provide a strong baseline on which others can build upon. To the best of our knowledge,these provide state-of-the-art result on Dutch F3 data set. We have released the code and the models in an open-source GitHub repository with permissive MIT license © EAGE 2019.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Deep learning Algorithm and Application Based on Convolutional Neural Network 1

引用

Annual International Conference on 3D Imaging Technology, IC3DIT 2019

作者： Guo, Mei Xiao, Min Yu, Fang College of Software and Communication Engineering Xiangnan University ChenzhouHunan423000 China

ISBN: (数字)9789811538636

ISBN: (纸本)9789811538629

The field of artificial intelligence has developed rapidly this year, and new high-tech companies with their main business have sprung up. After years of theoretical knowledge accumulation and computer hardware equipment upgrade, deep learning began to show its talents in the field of artificial intelligence such as computer vision and voice processing. Deep learning is mainly based on multi-layer neural network to imitate, learn, and apply images, texts, and voices. As one of the deep learning algorithms, convolutional neural networks are favored by researchers in related fields because of their local connections and the advantages of weight sharing. On the basis of expounding the deep learning algorithm of convolutional neural networks at home and abroad, this paper analyzes and summarizes the application of deep learning algorithm by convolutional neural networks and prospects its development trend, hoping to engage related convolutional neural networks. Provided a reference for researchers. © Springer Nature Singapore Pte Ltd. 2020.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A scenario-adaptive online learning algorithm for demand response

A scenario-adaptive online learning algorithm for demand res...

引用

2020 IEEE Power and Energy Society General Meeting, PESGM 2020

作者： Sang, Linwei Hu, Qinran Zhao, Yuan Han, Rushuai Wu, Zaijun Dou, Xiaobo Southeast University School of Electric Engineering Nanjing China

ISBN: (纸本)9781728155081

This paper introduces a scenario-adaptive online learning algorithm for aggregating demand side resources. The problem of dispatching demands is formulated under a contextual combinatorial multi-armed bandit framework with the objective to minimize the mismatch between actual aggregated demand adjustment and the reduction target from system operator. Comparing with previous online learning framework for demand aggregation, this paper considers temporal and spatial factors and creates a scenario-adaptive mechanism to model the behavior of demands. The simulation results show the proposed method achieves less mismatch and more reliable aggregation performance than conventional methods. © 2020 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Designing optimal dynamic treatment regimes: A causal reinforcement learning approach 37

Designing optimal dynamic treatment regimes: A causal reinfo...

引用

37th International Conference on Machine learning, ICML 2020

作者： Zhang, Junzhe Bareinboim, Elias Department of Computer Science Columbia University New York United States

ISBN: (纸本)9781713821120

A dynamic treatment regime (DTR) consists of a sequence of decision rules, one per stage of intervention, that dictates how to determine the treatment assignment to patients based on evolving treatments and covariates history. These regimes are particularly effective for managing chronic disorders and is arguably one of the critical ingredients underlying more personalized decisionmaking systems. All reinforcement learning algorithms for finding the optimal DTR in online settings will suffer ( p jDX[SjT) regret on some environments, where T is the number of experiments and DX[S is the domains of the treatments X and covariates S. This implies that T = (jDX[Sj) trials will be required to generate an optimal DTR. In many applications, the domains of X and S could be enormous, which means that the time required to ensure appropriate learning may be unattainable. We show that, if the causal diagram of the underlying environment is provided, one could achieve regret that is exponentially smaller than DX[S. In particular, we develop two online algorithms that satisfy such regret bounds by exploiting the causal structure underlying the DTR;one is the based on the principle of optimism in the face of uncertainty (OFU-DTR), and the other uses the posterior sampling learning (PS-DTR). Finally, we introduce efficient methods to accelerate these online learning procedures by leveraging the abundant, yet biased observational (non-experimental) data. © 2020 by the Authors All rights reserved.

关键词： learning algorithms

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：