检索结果-内蒙古大学图书馆

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Gupta, Raj Kumar Naveena, N. Rao, B. Srinivasa Rs, Rajasree Sarkar, Swagata Kumar, Kallakunta Ravi Sardar Vallabhbhai Patel College Veer Kunwar Singh University Physics Department Bihar Ara Bhabua India Kongu Engineering College Computer Technology-UG Perundurai India Gokaraju Rangaraju Institute of Engineering & Technology Department of Computer Science and Engineering Hyderabad500090 India New Horizon College of Engineering Artificial Intelligence and Machine Learning Bangalore India Sri Sairam Engineering College Department of Artificial Intelligence and Data Science Sai Leo Nagar Chennai44 India Koneru Lakshmaiah Education Foundation Department of Ece AP Vaddeswaram India

ISBN: (纸本)9798350321425

In minority class and noisy data situations, supervised learning performs more favorably for the majority class but cannot generalize testing data. Performance in the aforementioned use cases might be improved with the help of neural-based data augmentation approaches for generating new data and deep convolutional models for classification. GANs (generative adversarial networks) have recently demonstrated impressive advancements in picture generation. To address the restrictions imposed by the distribution bias problem between the produced data and the unique data, and to provide a more vigorous data augmentation, the presented distribution bias aware collaborative GAN (DGAN) model for unbalanced deep learning in industrial IoT. By including an auxiliary classifier in the foundational GAN model, a comprehensive data augmentation system may be built. In particular, a provisional source of energy with random labels is envisioned and trained combatively with the classification model to appropriately augment the amount of data specimens in minority classes, and a mass fraction system is newly envisioned between two distinct feature extraction, allowing the cooperative adversarial training among some of the power source, voltage divider, and classification algorithm. The next step is to develop an augmentation approach for smart anomaly detection in class imbalance, which, by adjusting for dispersion bias using the properly balanced data, might significantly improve classification precision. Experiment assessments using real-world unbalanced datasets show the superior recital of the suggested model in addressing the distribution biased issue for multi-class classification in class imbalance for commercial IoT applications, as compared to five baseline techniques. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Well-posedness of an evaporation model for a spherical droplet exposed to an air flow

arXiv

引用

arXiv 2023年

作者： Bänsch, Eberhard Doß, Martin Gräser, Carsten Ray, Nadja Department of Mathematics Friedrich-Alexander University Erlangen-Nürnberg Erlangen Germany Mathematical Institute for Machine Learning and Data Science Catholic University Eichstätt-Ingolstadt Ingolstadt Germany

MSC Codes 35Q79 (Primary) 35A01, 35K55, 80A19, 80M10 (Secondary)In this paper, we address the well-posedness of an evaporation model for a spherical liquid droplet taking into account the convective impact of an air flow in the ambient gas phase. From a mathematical perspective, we are dealing with a coupled ODE-PDE system for the droplet radius, the temperature distribution, and the vapor concentration. The nonlinear coupling arises from the evaporation rate modeled by the Hertz-Knudsen equation. Under physically meaningful assumptions, we prove existence and uniqueness of a weak solution until the droplet has evaporated completely. Numerical simulations are performed to illustrate how different air flows affect the evaporation process. Copyright © 2023, The Authors. All rights reserved.

关键词： Numerical models

来源：评论

学校读者我要写书评

暂无评论

PASS: Peer-Agreement based Sample Selection for Training with Noisy Labels

arXiv

引用

arXiv 2023年

作者： Garg, Arpit Nguyen, Cuong Felix, Rafael Do, Thanh-Toan Carneiro, Gustavo Australian Institute for Machine Learning University of Adelaide Australia Centre for Vision Speech and Signal Processing University of Surrey United Kingdom Department of Data Science and AI Monash University Australia

The prevalence of noisy-label samples poses a significant challenge in deep learning, inducing overfitting effects. This has, therefore, motivated the emergence of learning with noisy-label (LNL) techniques that focus on separating noisy- and clean-label samples to apply different learning strategies to each group of samples. Current methodologies often rely on the small-loss hypothesis or feature-based selection to separate noisy- and clean-label samples, yet our empirical observations reveal their limitations, especially for labels with instance dependent noise (IDN). An important characteristic of IDN is the difficulty to distinguish the clean-label samples that lie near the decision boundary (i.e., the hard samples) from the noisy-label samples. We, therefore, propose a new noisy-label detection method, termed Peer-Agreement based Sample Selection (PASS), to address this problem. Utilising a trio of classifiers, PASS employs consensus-driven peer-based agreement of two models to select the samples to train the remaining model. PASS is easily integrated into existing LNL models, enabling the improvement of the detection accuracy of noisy- and clean-label samples, which increases the classification accuracy across various LNL benchmarks. 1 Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Instance-dependent Noisy-label learning with Graphical Model Based Noise-rate Estimation

arXiv

引用

arXiv 2023年

作者： Garg, Arpit Nguyen, Cuong Felix, Rafael Do, Thanh-Toan Carneiro, Gustavo Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science and AI Monash University Australia Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of label noise arising from ambiguous sample information. To address IDN, Label Noise learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples. This stage uses an arbitrary criterion and a pre-defined curriculum that initially selects most samples as noisy and gradually decreases this selection rate during training. Such curriculum is sub-optimal since it does not consider the actual label noise rate in the training set. This paper addresses this issue with a new noise-rate estimation method that is easily integrated with most state-of-the-art (SOTA) LNL methods to produce a more effective curriculum. Synthetic and real-world benchmarks’ results demonstrate that integrating our approach with SOTA LNL methods improves accuracy in most cases. © 2023, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling

arXiv

引用

arXiv 2023年

作者： Zhao, Jingwei Xia, Gus Wang, Ziyu Wang, Ye Institute of Data Science NUS Singapore School of Computing NUS Singapore Integrative Sciences and Engineering Programme NUS Graduate School Singapore Machine Learning Department MBZUAI United Arab Emirates Computer Science Department NYU Shanghai China

In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing computational efficiency. In this paper, we introduce a novel system that leverages prior modelling over disentangled style factors to address these challenges. Our method presents a two-stage process: initially, a piano arrangement is derived from the lead sheet by retrieving piano texture styles;subsequently, a multi-track orchestration is generated by infusing orchestral function styles into the piano arrangement. Our key design is the use of vector quantization and a unique multi-stream Transformer to model the long-term flow of the orchestration style, which enables flexible, controllable, and structured music generation. Experiments show that by factorizing the arrangement task into interpretable sub-stages, our approach enhances generative capacity while improving efficiency. Additionally, our system supports a variety of music genres and provides style control at different composition hierarchies. We further show that our system achieves superior coherence, structure, and overall arrangement quality compared to existing baselines. © 2023, CC BY.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

On proximal policy optimization's heavy-tailed gradients

arXiv

引用

arXiv 2021年

作者： Garg, Saurabh Zhanson, Joshua Parisotto, Emilio Prasad, Adarsh Kolter, J. Zico Lipton, Zachary C. Balakrishnan, Sivaraman Salakhutdinov, Ruslan Ravikumar, Pradeep Machine Learning Department Carnegie Mellon University Computer Science Department Carnegie Mellon University Department of Statistics and Data Science Carnegie Mellon University

Modern policy gradient algorithms such as Proximal Policy Optimization (PPO) rely on an arsenal of heuristics, including loss clipping and gradient clipping, to ensure successful learning. These heuristics are reminiscent of techniques from robust statistics, commonly used for estimation in outlier-rich ("heavy-tailed") regimes. In this paper, we present a detailed empirical study to characterize the heavy-tailed nature of the gradients of the PPO surrogate reward function. We demonstrate that the gradients, especially for the actor network, exhibit pronounced heavy-tailedness and that it increases as the agent's policy diverges from the behavioral policy (i.e., as the agent goes further off policy). Further examination implicates the likelihood ratios and advantages in the surrogate reward as the main sources of the observed heavy-tailedness. We then highlight issues arising due to the heavy-tailed nature of the gradients. In this light, we study the effects of the standard PPO clipping heuristics, demonstrating that these tricks primarily serve to offset heavytailedness in gradients. Thus motivated, we propose incorporating GMOM, a high-dimensional robust estimator, into PPO as a substitute for three clipping tricks. Despite requiring less hyperparameter tuning, our method matches the performance of PPO (with all heuristics enabled) on a battery of MuJoCo continuous control tasks. © 2021, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Overview of machine learning for Bioengineering EEG Signal Processing

Overview of Machine Learning for Bioengineering EEG Signal P...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Siddhi Dhande Aahash Kamble Swapnil Gundewar Naathi Naresh Babu Praveen Kumar Department of Computer Science and Medical Engineering Datta Meghe Institute of Higher Education and Research Wardha India Department of Artificial Intellegence and Data Science Datta Meghe institute of Higher Education and Research(DU) Wardha Maharashtra Department of Artificial Intellegence and Machine Learning Datta Meghe institute of Higher Education and Research Wardha India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

Electroencephalography (EEG) is a well-established method in neuroscience and bioengineering that offers valuable information about brain function. Recent technological advancements have led to more complex EEG recordings, which necessitate more advanced analysis techniques. machine learning has emerged as an asset in EEG signal processing, enabling novel approaches to comprehension and utilization of brain activity. This article provides an in-depth analysis of the intersection of machine learning and EEG signal processing in bioengineering applications. This text presents a comprehensive overview of EEG data analysis techniques, focusing on the key steps of acquisition, preprocessing, and feature extraction. It highlights the challenges and strategies used to extract valuable information from raw EEG recordings. Additionally, it surveys various machine learning algorithms, including classic and modern deep learning methods, demonstrating their effectiveness in analyzing EEG signals and opening new frontiers in the field of bioengineering. This paper explores the growing connection between machine learning and EEG signal processing, examining how they work together to enhance healthcare, neurotechnology, and our knowledge of the brain. By studying existing research and cutting-edge developments, this study intends to focus on this synergistic relationship and its importance in these fields.

关键词： Neurological diseases Deep learning Technological innovation machine learning algorithms Medical services Feature extraction Electroencephalography Recording Neurotechnology Biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

Functional Linear Non-Gaussian Acyclic Model for Causal Discovery

arXiv

引用

arXiv 2024年

作者： Yang, Tian-Le Lee, Kuang-Yao Zhang, Kun Suzuki, Joe Graduate School of Engineering Science Osaka University 1-3 Machikaneyama Osaka Toyonaka Japan Department of Statistics Operations and Data Science Temple University PhiladelphiaPA19122 United States Machine Learning Department Carnegie Mellon University Mohamed bin Zayed University of Artificial Intelligence PittsburghPA15213 United States Masdar city Abu Dhabi United Arab Emirates

In causal discovery, non-Gaussianity has been used to characterize the complete configuration of a Linear Non-Gaussian Acyclic Model (LiNGAM), encompassing both the causal ordering of variables and their respective connection strengths. However, LiNGAM can only deal with the finite-dimensional case. To expand this concept, we extend the notion of variables to encompass vectors and even functions, leading to the Functional Linear Non-Gaussian Acyclic Model (Func-LiNGAM). Our motivation stems from the desire to identify causal relationships in brain-effective connectivity tasks involving, for example, fMRI and EEG datasets. We demonstrate why the original LiNGAM fails to handle these inherently infinite-dimensional datasets and explain the availability of functional data analysis from both empirical and theoretical perspectives. We establish theoretical guarantees of the identifiability of the causal relationship among non-Gaussian random vectors and even random functions in infinite-dimensional Hilbert spaces. To address the issue of sparsity in discrete time points within intrinsic infinite-dimensional functional data, we propose optimizing the coordinates of the vectors using functional principal component analysis. Experimental results on synthetic data verify the ability of the proposed framework to identify causal relationships among multivariate functions using the observed samples. For real data, we focus on analyzing the brain connectivity patterns derived from fMRI data. © 2024, CC BY.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Optimization without Retraction on the Random Generalized Stiefel Manifold

arXiv

引用

arXiv 2024年

作者： Vary, Simon Ablin, Pierre Gao, Bin Absil, P.-A. ICTEAM Institute UCLouvain Louvain-la-Neuve Belgium Department of Statistics University of Oxford Oxford United Kingdom Apple Machine Learning Group Paris France Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

Optimization over the set of matrices X that satisfy XτBX = Ip, referred to as the generalized Stiefel manifold, appears in many applications involving sampled covariance matrices such as the canonical correlation analysis (CCA), independent component analysis (ICA), and the generalized eigenvalue problem (GEVP). Solving these problems is typically done by iterative methods that require a fully formed B. We propose a cheap stochastic iterative method that solves the optimization problem while having access only to random estimates of B. Our method does not enforce the constraint in every iteration;instead, it produces iterations that converge to critical points on the generalized Stiefel manifold defined in expectation. The method has lower per-iteration cost, requires only matrix multiplications, and has the same convergence rates as its Riemannian optimization counterparts that require the full matrix B. Experiments demonstrate its effectiveness in various machine learning applications involving generalized orthogonality constraints, including CCA, ICA, and the *** Codes 90C26, 90C15 Copyright © 2024, The Authors. All rights reserved.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

RVPD: An Automated System for Calculating the Tortuosity and Bifurcation Angles of Retinal Vessels to Predict Diseases 22

RVPD: An Automated System for Calculating the Tortuosity and...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Yang, Guangzhengao Luo, Xingyu Zhao, Jie Fan, Fangfang Li, Haoshen Dong, Bin Zhang, Li Zhang, Yan Center for Data Science Peking University China Peking University First Hospital Department of Cardiology China National Engineering Laboratory for Big Data Analysis and Applications Peking University China Peking University Changsha Institute for Computing and Digital Economy China Beijing International Center for Mathematical Research Peking University China Center for Machine Learning Research Peking University China National Biomedical Imaging Center Peking University China

ISBN: (纸本)9798331520526

Hypertension and diabetes are known to potentially cause morphological changes in the retinal capillary system, yet quantifying these changes presents significant challenges. This research addresses this issue by designing and developing an automated system capable of analyzing retinal images to detect and measure these changes. Our system automatically segments vessels and the optic disc, calculates tortuosity and bifurcation angles, and performs disease prediction based on these measurements along with clinical features. For tortuosity calculation, we adopted a novel curve fitting method, which provides more stable convergence compared to traditional discrete numerical methods. The system integrates clinical data and conducts prediction experiments on hypertensive and diabetic patients with varying sample sizes. Our results demonstrate the system's strong performance and scalability: in the hypertension group, the AUC reached a maximum of 0.814 ± 0.023, with an ACC of 0.735 ± 0.033, while in the diabetes group, the AUC reached a maximum of 0.710 ± 0.043, with an ACC of 0.641 ± 0.052. These findings suggest that our automated system could serve as a valuable tool for early detection and risk assessment of hypertension and diabetes, potentially improving patient outcomes through timely intervention. © 2025 IEEE.

关键词： Bifurcation Diabetes Hypertension Retinal vessel segmentation Tortuosity

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：