Foundations and Trends in Machine Learning最新文献_第3页

Predictions of Steady and Unsteady Flows using Machine-learned Surrogate Models 用机器学习代理模型预测定常和非定常流动

IF 32.8

Foundations and Trends in Machine Learning Pub Date : 2020-11-01 DOI: 10.1109/MLHPCAI4S51975.2020.00016

S. Bhushan, G. Burgreen, Joshua Bowman, I. Dettwiller, W. Brewer

{"title":"Predictions of Steady and Unsteady Flows using Machine-learned Surrogate Models","authors":"S. Bhushan, G. Burgreen, Joshua Bowman, I. Dettwiller, W. Brewer","doi":"10.1109/MLHPCAI4S51975.2020.00016","DOIUrl":"https://doi.org/10.1109/MLHPCAI4S51975.2020.00016","url":null,"abstract":"The applicability of computational fluid dynamics (CFD) based design tools depend on the accuracy and complexity of the physical models, for example turbulence models, which remains an unsolved problem in physics, and rotor models that dictates the computational cost of rotorcraft and wind/hydro turbine farm simulations. The research focuses on investigation of the ability of neural networks to learn correlation between desired modeling variables and flow parameters, thereby providing surrogate models. For the turbulence modeling, the machine learned turbulence model is developed for unsteady boundary layer flow, and the predictions are validated against DNS data and compared with one-equation unsteady Reynolds Averaged Navier-Stokes (URANS) predictions. The machine-learned model performs much better than the URANS model due to its ability to incorporate the non-linear correlation between turbulent stresses and rate-of-strain. The development of the surrogate rotor model builds on the hypothesis that if a model can mimic the axial and tangential momentum deficit generated by a blade resolved model, then it should produce a qualitatively and quantitatively similar wake recovery. An initial validation of the hypothesis was performed, which showed encouraging results.","PeriodicalId":47667,"journal":{"name":"Foundations and Trends in Machine Learning","volume":"67 1","pages":"80-87"},"PeriodicalIF":32.8,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91118522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Automatic Particle Trajectory Classification in Plasma Simulations 等离子体模拟中的粒子轨迹自动分类

IF 32.8

Foundations and Trends in Machine Learning Pub Date : 2020-10-11 DOI: 10.1109/MLHPCAI4S51975.2020.00014

S. Markidis, I. Peng, Artur Podobas, Itthinat Jongsuebchoke, Gabriel Bengtsson, Pawel Herman

{"title":"Automatic Particle Trajectory Classification in Plasma Simulations","authors":"S. Markidis, I. Peng, Artur Podobas, Itthinat Jongsuebchoke, Gabriel Bengtsson, Pawel Herman","doi":"10.1109/MLHPCAI4S51975.2020.00014","DOIUrl":"https://doi.org/10.1109/MLHPCAI4S51975.2020.00014","url":null,"abstract":"Numerical simulations of plasma flows are crucial for advancing our understanding of microscopic processes that drive the global plasma dynamics in fusion devices, space, and astrophysical systems. Identifying and classifying particle trajectories allows us to determine specific on-going acceleration mechanisms, shedding light on essential plasma processes.Our overall goal is to provide a general workflow for exploring particle trajectory space and automatically classifying particle trajectories from plasma simulations in an unsupervised manner. We combine pre-processing techniques, such as Fast Fourier Transform (FFT), with Machine Learning methods, such as Principal Component Analysis (PCA), k-means clustering algorithms, and silhouette analysis. We demonstrate our workflow by classifying electron trajectories during magnetic reconnection problem. Our method successfully recovers existing results from previous literature without a priori knowledge of the underlying system.Our workflow can be applied to analyzing particle trajectories in different phenomena, from magnetic reconnection, shocks to magnetospheric flows. The workflow has no dependence on any physics model and can identify particle trajectories and acceleration mechanisms that were not detected before.","PeriodicalId":47667,"journal":{"name":"Foundations and Trends in Machine Learning","volume":"9 1","pages":"64-71"},"PeriodicalIF":32.8,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90705025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Deep Learning-based Low-dose Tomography Reconstruction with Hybrid-dose Measurements 基于混合剂量测量的深度学习低剂量断层扫描重建

IF 32.8

Foundations and Trends in Machine Learning Pub Date : 2020-09-28 DOI: 10.1109/MLHPCAI4S51975.2020.00017

Ziling Wu, Tekin Bicer, Zhengchun Liu, V. De Andrade, Yunhui Zhu, Ian T Foster

{"title":"Deep Learning-based Low-dose Tomography Reconstruction with Hybrid-dose Measurements","authors":"Ziling Wu, Tekin Bicer, Zhengchun Liu, V. De Andrade, Yunhui Zhu, Ian T Foster","doi":"10.1109/MLHPCAI4S51975.2020.00017","DOIUrl":"https://doi.org/10.1109/MLHPCAI4S51975.2020.00017","url":null,"abstract":"Synchrotron-based X-ray computed tomography is widely used for investigating inner structures of specimens at high spatial resolutions. However, potential beam damage to samples often limits the X-ray exposure during tomography experiments. Proposed strategies for eliminating beam damage also decrease reconstruction quality. Here we present a deep learning-based method to enhance low-dose tomography reconstruction via a hybrid-dose acquisition strategy composed of extremely sparse-view normal-dose projections and full-view low-dose projections. Corresponding image pairs are extracted from low-/normal-dose projections to train a deep convolutional neural network, which is then applied to enhance full-view noisy low-dose projections. Evaluation on two experimental datasets under different hybrid-dose acquisition conditions show significantly improved structural details and reduced noise levels compared to uniformly distributed acquisitions with the same number of total dosage. The resulting reconstructions also preserve more structural information than reconstructions processed with traditional analytical and regularization-based iterative reconstruction methods from uniform acquisitions. Our performance comparisons show that our implementation, HDrec, can perform denoising of a real-world experimental data 410x faster than the state-of-the-art X-learn method while providing better quality. This framework can be applied to other tomographic or scanning based X-ray imaging techniques for enhanced analysis of dose-sensitive samples and has great potential for studying fast dynamic processes.","PeriodicalId":47667,"journal":{"name":"Foundations and Trends in Machine Learning","volume":"96 1","pages":"88-95"},"PeriodicalIF":32.8,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76868787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models 解决偏微分方程的深度生成模型:用于训练大型无数据模型的分布式计算

IF 32.8

Foundations and Trends in Machine Learning Pub Date : 2020-07-24 DOI: 10.1109/MLHPCAI4S51975.2020.00013

Sergio Botelho, Ameya Joshi, Biswajit Khara, S. Sarkar, C. Hegde, Santi S. Adavani, B. Ganapathysubramanian

{"title":"Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models","authors":"Sergio Botelho, Ameya Joshi, Biswajit Khara, S. Sarkar, C. Hegde, Santi S. Adavani, B. Ganapathysubramanian","doi":"10.1109/MLHPCAI4S51975.2020.00013","DOIUrl":"https://doi.org/10.1109/MLHPCAI4S51975.2020.00013","url":null,"abstract":"Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥ 1024 × 1024).Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods.We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2–3 × faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.","PeriodicalId":47667,"journal":{"name":"Foundations and Trends in Machine Learning","volume":"12 1","pages":"50-63"},"PeriodicalIF":32.8,"publicationDate":"2020-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78200054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Model-based Reinforcement Learning: A Survey 基于模型的强化学习:综述

IF 32.8

Foundations and Trends in Machine Learning Pub Date : 2020-06-30 DOI: 10.1561/9781638280576

T. Moerland, J. Broekens, C. Jonker

{"title":"Model-based Reinforcement Learning: A Survey","authors":"T. Moerland, J. Broekens, C. Jonker","doi":"10.1561/9781638280576","DOIUrl":"https://doi.org/10.1561/9781638280576","url":null,"abstract":"Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is a key challenge in artificial intelligence. Two key approaches to this problem are reinforcement learning (RL) and planning. This paper presents a survey of the integration of both fields, better known as model-based reinforcement learning. Model-based RL has two main steps. First, we systematically cover approaches to dynamics model learning, including challenges like dealing with stochasticity, uncertainty, partial observability, and temporal abstraction. Second, we present a systematic categorization of planning-learning integration, including aspects like: where to start planning, what budgets to allocate to planning and real data collection, how to plan, and how to integrate planning in the learning and acting loop. After these two key sections, we also discuss the potential benefits of model-based RL, like enhanced data efficiency, targeted exploration, and improved stability. Along the survey, we also draw connections to several related RL fields, like hierarchical RL and transfer, and other research disciplines, like behavioural psychology. Altogether, the survey presents a broad conceptual overview of planning-learning combinations for MDP optimization.","PeriodicalId":47667,"journal":{"name":"Foundations and Trends in Machine Learning","volume":"34 1","pages":"1-118"},"PeriodicalIF":32.8,"publicationDate":"2020-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67081990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12