检索结果-内蒙古大学图书馆

Recent advances and applications of deep learning methods in materials science

npj Computational Materials 2022年第1期8卷 548-573页

作者： Kamal Choudhary Brian DeCost Chi Chen Anubhav Jain Francesca Tavazza Ryan Cohn Cheol Woo Park Alok Choudhary Ankit Agrawal Simon J.L.Billinge Elizabeth Holm Shyue Ping Ong Chris Wolverton Materials Science and Engineering Division National Institute of Standards and TechnologyGaithersburgMD20899USA Theiss Research La JollaCA92037USA DeepMaterials LLC Silver SpringMD20906USA Material Measurement Science Division National Institute of Standards and TechnologyGaithersburgMD20899USA Department of NanoEngineering University of California San DiegoSan DiegoCA92093USA Energy Technologies Area Lawrence Berkeley National LaboratoryBerkeleyCAUSA Department of Materials Science and Engineering Carnegie Mellon UniversityPittsburghPA15213USA Department of Materials Science and Engineering Northwestern UniversityEvanstonIL60208USA Department of Electrical and Computer Engineering Northwestern UniversityEvanstonIL60208USA Department of Applied Physics and Applied Mathematics and the Data Science Institute Fu Foundation School of Engineering and Applied SciencesColumbia UniversityNew YorkNY10027USA

Deep learning(DL)is one of the fastest-growing topics in materials data science,with rapidly emerging applications spanning atomistic,image-based,spectral,and textual data *** allows analysis of unstructured data and automated identification of *** recent development of large materials databases has fueled the application of DL methods in atomistic prediction in *** contrast,advances in image and spectral data have largely leveraged synthetic data enabled by high-quality forward models as well as by generative unsupervised DL *** this article,we present a high-level overview of deep learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation,materials imaging,spectral analysis,and natural language *** each modality we discuss applications involving both theoretical and experimental data,typical modeling approaches with their strengths and limitations,and relevant publicly available software and *** conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations,challenges,and potential growth areas for DL methods in materials science.

关键词： learning limitations textual

来源：评论

学校读者我要写书评

暂无评论

Anisotropic Double Phase Elliptic Inclusion Systems with Logarithmic Perturbation and Multivalued Convections

引用

applied mathematics & Optimization 2025年第1期92卷 1-41页

作者： Zeng, Shengda Lu, Yasi Rădulescu, Vicenţiu D. National Center for Applied Mathematics in Chongqing and School of Mathematical Sciences Chongqing Normal University Chongqing China College of Mathematics and Information Science Guangxi University Nanning P.R. China Faculty of Applied Mathematics AGH University of Kraków Kraków Poland Department of Mathematics University of Craiova Craiova Romania Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic

In this paper, we investigate a class of variable exponent double phase elliptic inclusion systems involving anisotropic partial differential operators with logarithmic perturbation as well as two fully coupled multivalued terms, one of them is defined in the domain and the other is defined on the boundary, respectively. Firstly, under the suitable coercive conditions, the existence of a weak solution for the double phase elliptic inclusion systems is verified via applying a surjectivity theorem concerning multivalued pseudomonotone operators. Then, when the elliptic inclusion system is considered in non-coercive framework, we employ the sub-supersolution method to establish the existence and compactness results. Finally, we deliver several solvability properties of some special cases with respect to the elliptic inclusion system under consideration via constructing proper sub- and super-solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating Multiscale Mapper Features with Machine Learning Techniques to Improve Breast Cancer Classification Accuracy

Integrating Multiscale Mapper Features with Machine Learning...

引用

IEEE/ACM International Symposium on Big Data Computing (BDC)

作者： Rabelani Netshifhire Maria Vivien Visaya Department of Electrical and Electronic Engineering Science University of Johannesburg Johannesburg South Africa Department of Mathematics and Applied Mathematics University of Johannesburg Johannesburg South Africa DSI-NRF CoE-MaSS Johannesburg South Africa

ISBN: (数字)9798350367300

ISBN: (纸本)9798350367317

Breast cancer classification is critical for early detection and treatment planning. The complexity of breast cancer data poses feature engineering challenges for conventional machine learning (ML) methods, which often fail to capture these *** employ the Mapper algorithm, a topological data analysis (TDA) tool, for feature engineering. Two variants of Mapper algorithm are utilized, namely Singlescale Mapper (SM) and Multiscale Mapper (MM). SM is constrained by scale sensitivity, dimensionality limitations, and parameter tuning challenges. MM enhance SM by capturing topological features at multiple resolutions, offering a robust hierarchical view of *** the Wisconsin Breast Cancer Diagnostic (WBCD) dataset, three feature sets namely conventional, SM-derived, and MM-derived features are evaluated across various selected ML models to assess their potential to enhance classification *** demonstrated that MM-derived features integrated with ML models improved breast cancer classification accuracy, outperforming both conventional and SM-derived features. This findings highlight the potential of TDA’s MM as a feature engineering tool to improve breast cancer classification.

关键词： Accuracy Machine learning algorithms Data analysis Sensitivity Machine learning Feature extraction Breast cancer Planning Classification algorithms Tuning

来源：评论

学校读者我要写书评

暂无评论

Long Sequence Decoder Network for Mobile Sensing

arXiv

引用

arXiv 2024年

作者： Mei, Jiazhong Kutz, J. Nathan Department of Applied Mathematics University of Washington SeattleWA98195 United States Department of Electrical and Computer Engineering University of Washington SeattleWA98195 United States

The reconstruction and estimation of spatio-temporal patterns poses significant challenges when sensor measurements are limited. The use of mobile sensors adds additional complexity due to the change in sensor locations over time. In such cases, historical measurement and sensor information are useful for better performance, including models such as Kalman filters, recurrent neural networks (RNNs) or transformer models. However, many of these approaches often fail to efficiently handle long sequences of data in such scenarios and are sensitive to noise. In this paper, we consider a model-free approach using the structured state space sequence (S4D) model as a deep learning layer in traditional sequence models to learn a better representation of historical sensor data. Specifically, it is integrated with a shallow decoder network for reconstruction of the high-dimensional state space. We also introduce a novel initialization of the S4D model using a Butterworth filter design to reduce noise in the inputs. Consequently, we construct a robust S4D (rS4D) model by appending the filtering S4D layer before the original S4D structure. This robust variant enhances the capability to accurately reconstruct spatio-temporal patterns with noisy mobile sensor measurements in long sequence. Numerical experiments demonstrate that our model achieves better performance compared with previous approaches. Our results underscore the efficacy of leveraging state space models within the context of spatio-temporal data reconstruction and estimation using limited mobile sensor resources, particularly in terms of long-sequence dependency and robustness to noise. © 2024, CC0.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Design of Multi-Dimensional Spatially-Coupled Codes

Probabilistic Design of Multi-Dimensional Spatially-Coupled ...

引用

IEEE International Symposium on Information Theory

作者： Canberk İrimağzı Ata Tanrıkulu Ahmed Hareedy Institute of Applied Mathematics Middle East Technical University Ankara Turkey Department of Electrical and Electronics Engineering Middle East Technical University Ankara Turkey

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

Because of their excellent asymptotic and finite-length performance, spatially-coupled (SC) codes are a class of low-density parity-check codes that is gaining increasing attention. Multi-dimensional (MD) SC codes are constructed by connecting copies of an SC code via relocations in order to mitigate various sources of non-uniformity and improve performance in many data storage and data transmission systems. As the number of degrees of freedom in the MD-SC code design increases, appropriately exploiting them becomes more difficult because of the complexity growth of the design process. In this paper, we propose a probabilistic framework for the MD-SC code design, which is based on the gradient-descent (GD) algorithm, to design better MD codes and address this challenge. In particular, we express the expected number of short cycles, which we seek to minimize, in the graph representation of the code in terms of entries of a probability-distribution matrix that characterizes the MD-SC code design. We then find a locally-optimal probability distribution, which serves as the starting point of a finite-length algorithmic optimizer that produces the final MD-SC code. We offer the theoretical analysis as well as the algorithms, and we present experimental results demonstrating that our MD codes, conveniently called GD-MD codes, have notably lower short cycle numbers compared with the available state-of-the-art. Moreover, our algorithms converge on solutions in few iterations, which confirms the complexity reduction as a result of limiting the search space via the locally-optimal GD-MD distributions.

关键词： Codes Limiting Memory Probabilistic logic Probability distribution Parity check codes Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Distributed Subgradient

Heterogeneous Distributed Subgradient

引用

American Control Conference (ACC)

作者： Yixuan Lin Marco Gamarra Ji Liu Meta and was previously affiliated with the Department of Applied Mathematics and Statistics Stony Brook University Air Force Research Laboratory Department of Electrical and Computer Engineering Stony Brook University

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

The paper proposes a heterogeneous push-sum based subgradient algorithm for multi-agent distributed convex optimization, in which each agent can arbitrarily switch between subgradient-push and push-subgradient at any time. It is shown that the heterogeneous algorithm converges to an optimal point at an optimal rate over time-varying directed graphs. The switching process within the heterogeneous algorithm can help prevent the leakage of agents' subgradient information.

关键词： Directed graphs Switches Convex functions

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Particle Sorting for Cryo-EM using Probabilistic PCA

Unsupervised Particle Sorting for Cryo-EM using Probabilisti...

引用

IEEE International Symposium on Biomedical Imaging

作者： Gili Weiss-Dicker Amitay Eldar Yoel Shkolinsky Tamir Bendory School of Electrical Engineering Tel Aviv University Department of Applied Mathematics School of Mathematical Sciences Tel Aviv University

Single-particle cryo-electron microscopy (cryo-EM) is a leading technology to resolve the structure of molecules. Early in the process, the user detects potential particle images in the raw data. Typically, there are many false detections as a result of high levels of noise and contamination. Currently, removing the false detections requires human intervention to sort the hundred thousands of images. We propose a statistically-established unsupervised algorithm to remove non-particle images. We model the particle images as a union of low-dimensional subspaces, assuming non-particle images are arbitrarily scattered in the high-dimensional space. The algorithm is based on an extension of the probabilistic PCA framework to robustly learn a non-linear model of union of subspaces. This provides a flexible model for cryo-EM data, and allows to automatically remove images that correspond to pure noise and contamination. Numerical experiments corroborate the effectiveness of the sorting algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistical mechanics and pressure of composite multimoded weakly nonlinear optical systems

arXiv

引用

arXiv 2024年

作者： Efremidis, Nikolaos K. Christodoulides, Demetrios N. Department of Applied Mathematics University of Crete Heraklion71409 Greece Institute of Applied and Computational Mathematics FORTH Crete Heraklion70013 Greece Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States

Statistical mechanics can provide a versatile theoretical framework for investigating the collective dynamics of weakly nonlinear waves-settings that can be utterly complex to describe otherwise. In optics, composite systems arise due to interactions between different frequencies and/or polarizations. The purpose of this work is to develop a thermodynamic theory that takes into account the synergistic action of multiple components. We find that the type of the nonlinearity involved can have important implications in the thermalization process and, hence, can lead to different thermal equilibrium conditions. Importantly, we derive closed-form expressions for the actual optomechanical pressure that is exerted on the system. In particular, the total optomechanical pressure is the sum of the partial pressures due to each component. Our results can be applied to a variety of weakly nonlinear optical settings such as multimode fibers, bulk waveguides, photonic lattices, and coupled microresonators. We present two specific examples, where two colors interact in a waveguide array with either a cubic or quadratic nonlinearity. Copyright © 2024, The Authors. All rights reserved.

关键词： Statistical mechanics

来源：评论

学校读者我要写书评

暂无评论

On the Computational Determination of the Third Focus of the Cartesian Oval

On the Computational Determination of the Third Focus of the...

引用

Telecommunications Forum (TELFOR)

作者： Branko Malešević Aleksandra Rosić Bojan Banjac Miloš Mićović Department of Applied Mathematics School of Electrical Engineering University of Belgrade Belgrade Serbia Department of Algebra and Mathematical Logic Faculty of Mathematics University of Belgrade Belgrade Serbia Computer Graphics Chair Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia Intens DOO Novi Sad Serbia Department of Applied Mathematics Science and Research Centre School of Electrical Engineering University of Belgrade Belgrade Serbia

ISBN: (数字)9798350391060

ISBN: (纸本)9798350391077

In this paper, the correctness of the algebraic determination of the coordinate of the third focus of the Cartesian oval is examined and analysed. This analysis is necessary because the process includes solving systems with a large number of multivariate polynomial equations using the computer algebra system Maple. The paper also considers the difficulties and limitations of using computers in determining the coordinate of the third focus.

关键词： Geometry Computer science Algebra Optics Polynomials Mathematical models Telecommunications

来源：评论

学校读者我要写书评

暂无评论

A Reconfigurable Compute-In-Memory Design with Adaptive Bit-Precision and Power Adjustment

A Reconfigurable Compute-In-Memory Design with Adaptive Bit-...

引用

Consumer Technology (ICCT-Pacific), International Conference on

作者： I-Chieh Hsu Chun-Fu Chen Dao-Long Huang Yun-Kai Yeh Wei-Chieh Lee Qi-Hua Lin Jinjia Zhou I-Chyn Wey Electrical Engineering Department College of Engineering Chang-Gung University Taiwan School of Electrical Engineering National Taiwan University of Science and Technology Taiwan Master Program in Nano-Electronic Engineering and Design Chang Gung University Taiwan Department of Applied Informatics Faculty of Science and Engineering Hosei University Japan

ISBN: (数字)9798331504120

ISBN: (纸本)9798331504137

With the successful development of artificial intelligence (AI), Convolutional Neural Networks (CNNs) occupy a large amount of computing time and power consumption in the entire AI computing process. However, in traditional von Neumann architectures, the separation of the computing element and memory leads to the memory-wall problem of memory data transmission bandwidth from memory to processing element when executing multiply-accumulate-based CNN operations. The data transmission time and power consumption all are much higher than the CNN computing part. Therefore, this paper proposes a memory-in-computation design that can flexibly adjust energy usage, achieve high energy efficiency, and support multiple operation frequencies. By controlling the switches of each memory row, unnecessary energy consumption is avoided, leading to a reduction in total power consumption by 15% to 60%. Additionally, by adjusting the pulse width, the charging power consumption of capacitors is reduced by 65% per charge cycle.

关键词： Energy consumption Power demand Capacitors Bandwidth In-memory computing Control systems Energy efficiency Convolutional neural networks Data communication Artificial intelligence

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：