检索结果-内蒙古大学图书馆

55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021

作者： Neopane, Ojash Ramdas, Aaditya Singh, Aarti Carnegie Mellon University Machine Learning Department PittsburghPA United States Carnegie Mellon University Department of Statistics and Data Science PittsburghPA United States

ISBN: (纸本)9781665458283

We consider a variant of the best arm identification (BAI) problem in multi-armed bandits (MAB) in which there are two sets of arms (source and target), and the objective is to determine the best target arm while only pulling source arms. In this paper, we study the setting when, despite the means being unknown, there is a known additive relationship between the source and target MAB instances. We show how our framework covers a range of previously studied pure exploration problems and additionally captures new problems. We propose and theoretically analyze an LUCB-style algorithm to identify an e-optimal target arm with high probability. Our theoretical analysis highlights aspects of this transfer learning problem that do not arise in the typical BAI setup, and yet recover the LUCB algorithm for single domain BAI as a special case. © 2021 IEEE.

关键词： Additives

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 38

On Proximal Policy Optimization's Heavy-tailed Gradients

引用

38th International Conference on machine learning, ICML 2021

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

ISBN: (纸本)9781713845065

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 heavy-tailedness 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. Copyright © 2021 by the author(s)

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

RATT: Leveraging Unlabeled data to Guarantee Generalization 38

RATT: Leveraging Unlabeled Data to Guarantee Generalization

引用

38th International Conference on machine learning, ICML 2021

作者： Garg, Saurabh Balakrishnan, Sivaraman Zico Kolter, J. Lipton, Zachary C. Machine Learning Department Carnegie Mellon University United States Department of Statistics and Data Science Carnegie Mellon University United States Computer Science Department Carnegie Mellon University United States

ISBN: (纸本)9781713845065

To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on the true risk;or (ii) validate empirically on holdout data. However, (i) typically yields vacuous guarantees for overparameterized models;and (ii) shrinks the training set and its guarantee erodes with each reuse of the holdout set. In this paper, we leverage unlabeled data to produce generalization bounds. After augmenting our (labeled) training set with randomly labeled data, we train in the standard fashion. Whenever classifiers achieve low error on the clean data but high error on the random data, our bound ensures that the true risk is low. We prove that our bound is valid for 0-1 empirical risk minimization and with linear classifiers trained by gradient descent. Our approach is especially useful in conjunction with deep learning due to the early learning phenomenon whereby networks fit true labels before noisy labels but requires one intuitive assumption. Empirically, on canonical computer vision and NLP tasks, our bound provides non-vacuous generalization guarantees that track actual performance closely. This work enables practitioners to certify generalization even when (labeled) holdout data is unavailable and provides insights into the relationship between random label noise and generalization. Copyright © 2021 by the author(s)

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Traffic Incident Detection using Factor Analysis and Weighted Random Forest Algorithm 5

An Enhanced Traffic Incident Detection using Factor Analysis...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Kanna, P. Rajesh Vanithamani, S. Karunakaran, P. Pandiaraja, P. Tamilarasi, N. Nithin, P. Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamil Nadu Erode India M. Kumarasamy College of Engineering Department of Master of Computer Applications Tamil Nadu Karur India Nandha Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Erode India Vel Tech Rangarajan Dr. Sagunthala Department of Computer Science and Engineering R&D Institute of Science and Technology Tamil Nadu Chennai India Nehru Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Tamil Nadu Erode India

ISBN: (纸本)9798331518097

Efficient and precise traffic incident detection is essential to reduce casualties and property damage. To address the issue of unbalanced event data, this work offers a novel methodology known as FA-WRF (Factor Analysis and Weighted Random Forest). This approach combines dimensionality reduction through factor analysis with classification using weighted random forests, data preparation through the Synthetic Minority Over-Sampling Technique (SMOTE), and data preparation with SMOTE. The included feature of severity detection is highlighted, as are the performance metrics of the FA-WRF model using well-established metrics such as detection level rate, number of false count alarm rate, classification type rate, and area specification under the receiver operating characteristic curve (AUC). The superiority of the FA-WRF model is illustrated using real-world expressway traffic data represented by imbalanced incidents through thorough comparisons with various machine learning-based algorithms such as Support Vector machine, k-nearest neighbours algorithms, Logistic Regression algorithms, and decision-making trees. In addition to advancing incident detection, this technique has encouraging prospects for enhancing traffic management procedures and well-informed decision-making procedures in transportation networks. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

machine-learning Force Fields Reveal Shallow Electronic States on Dynamic Halide Perovskite Surfaces

arXiv

引用

arXiv 2025年

作者： Delgado, Frederico P. Simões, Frederico Kronik, Leeor Kaiser, Waldemar Egger, David A. Physics Department TUM School of Natural Sciences Technical University of Munich Germany Department of Molecular Chemistry and Materials Science Weizmann Institute of Science Israel Atomistic Modeling Center Munich Data Science Institute Technical University of Munich Germany Munich Center for Machine Learning Munich Germany

The spectacular performance of halide perovskites in optoelectronic devices is rooted in their favorable tolerance to structural defects. Previous studies showed that defects in these materials generate shallow electronic states that do not degrade device performance. However, how these shallow states persist amid the pronounced thermally-stimulated atomic dynamics on halide perovskite surfaces remains unknown. This work reveals that electronic states at surfaces of the prototypical CsPbBr3 variant are energetically distributed at room temperature, akin to well-passivated inorganic semiconductors, even when covalent bonds remain cleaved and undercoordinated. Specifically, a striking tendency for shallow surface states is found with approximately 70% of surface-state energies appearing within 0.2 eV or ≈8kBT from the valence-band edge. Furthermore, we show that even when surface states appear deeper in the gap, they are not energetically isolated and are less likely to act as traps. We achieve this result by accelerating first-principles calculations via machine-learning techniques and show that the unique atomic dynamics in these materials render the formation of deep electronic states at their surfaces unlikely. These findings reveal the microscopic mechanism behind the low density of deep defect states at dynamic halide perovskite surfaces, which is key to their exceptional performance in devices. © 2025, CC BY.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Personalised Speech-Based PTSD Prediction Using Weighted-Instance learning 46

Personalised Speech-Based PTSD Prediction Using Weighted-Ins...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Kathan, Alexander Amiriparian, Shahin Triantafyllopoulos, Andreas Gebhard, Alexander Milkus, Sabrina Hohmann, Jonas Muderlak, Pauline Schottdorf, Jürgen Musil, Richard Schuller, Björn W. University of Augsburg Eihw - Embedded Intelligence for Healthcare and Wellbeing Germany Mri Technical Univsersity of Munich Chi - Health Informatics Germany Mcml - Munich Center for Machine Learning Germany University Hospital Lmu Munich Department of Psychiatry and Psychotherapy Germany Zentrumspraxis Friedberg Germany Imperial College London Glam - Group on Language Audio & Music United Kingdom Mdsi - Munich Data Science Institute Germany

ISBN: (纸本)9798350371499

Post-traumatic stress disorder (PTSD) is a prevalent disorder that can develop in people who have experienced very stressful, shocking, or distressing events. It has great influence on peoples' daily life and can affect their mental, physical, or social wellbeing, which is why a timely and professional treatment is required. In this paper, we propose a personalised speech-based PTSD prediction approach using a newly collected dataset which consists of 15 participants, including speech recordings from people with PTSD and healthy controls. In addition, the dataset includes data before and after a clinical intervention so that the prediction can be analysed at different points in time. In our experiments, we demonstrate the superiority of the personalised approach, achieving a best area under the ROC curve (AUC) of 82 % and a best relative improvement of 7 % points compared to the non-personalised model. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Deep learning Based Fall Detection in Elderly People

A Comprehensive Review on Deep Learning Based Fall Detection...

引用

machine learning and Autonomous Systems (ICMLAS), International Conference on

作者： S. Venkata Suryanarayana Lakshmi H.N Posimsetti T Chiranjeevi Swamy D. Bhanu Mahesh Department of Computer Science and Engineering (Data Science) CVR College of Engineering Hyderabad India Department of Computer Science and Engineering (AI&ML) CVR College of Engineering Hyderabad India Department of Artificial Intelligence and Machine Learning Swarnandhra College of Engineering and Technology Narsapuram Andhra Pradesh India Department of Computer Science and Engineering KMIT Hyderabad India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Elderly people are more vulnerable to falls, which can result in serious injuries, a lower quality of life, and higher medical expenses. Traditional fall detection methods, such as wearable sensors or vision-based systems, face limitations in accuracy, comfort, and practicality. Recent advancements in deep learning have significantly improved fall detection capabilities by leveraging powerful computational models for data analysis and feature extraction. With an emphasis on important methodologies, architectures, and datasets utilized in the area, this paper offers a thorough literature analysis of deep learning-based fall detection strategies. It investigates several deep learning techniques applied to sensor-based and video-based fall detection systems, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hybrid models. The review also emphasizes the difficulties encountered in practical application, including data privacy and computing cost, and the need for robust datasets. Finally, future research directions are proposed to address current limitations and improve fall detection systems' dependability and effectiveness for elderly care.

关键词： Deep learning Recurrent neural networks Reviews Computational modeling Convolutional neural networks Fall detection Older adults Wearable sensors Long short term memory Injuries

来源：评论

学校读者我要写书评

暂无评论

Less is More: Facial Landmarks can Recognize a Spontaneous Smile 33

Less is More: Facial Landmarks can Recognize a Spontaneous S...

引用

33rd British machine Vision Conference Proceedings, BMVC 2022

作者： Tushar, Md Tahrim Faroque Yang, Yan Hossain, Md Zakir Naim, Sheikh Motahar Mohammed, Nabeel Rahman, Shafin Department of Electrical and Computer Engineering North South University Bangladesh Biological Data Science Institute The Australian National University Canberra Australia CSIRO Agriculture and Food Canberra Australia CSIRO Machine Learning and Artificial Intelligence Future Science Platform Canberra Australia Amazon Web Services

Smile veracity classification is a task of interpreting social interactions. Broadly, it distinguishes between spontaneous and posed smiles. Previous approaches used hand-engineered features from facial landmarks or considered raw smile videos in an end-to-end manner to perform smile classification tasks. Feature-based methods require intervention from human experts on feature engineering and heavy pre-processing steps. On the contrary, raw smile video inputs fed into end-to-end models bring more automation to the process with the cost of considering many redundant facial features (beyond landmark locations) that are mainly irrelevant to smile veracity classification. It remains unclear to establish discriminative features from landmarks in an end-to-end manner. We present a MeshSmileNet framework, a transformer architecture, to address the above limitations. To eliminate redundant facial features, our landmarks input is extracted from Attention Mesh, a pre-trained landmark detector. Again, to discover discriminative features, we consider the relativity and trajectory of the landmarks. For the relativity, we aggregate facial landmark that conceptually formats a curve at each frame to establish local spatial features. For the trajectory, we estimate the movements of landmark composed features across time by self-attention mechanism, which captures pairwise dependency on the trajectory of the same landmark. This idea allows us to achieve state-of-the-art performances on UVA-NEMO, BBC, MMI Facial Expression, and SPOS datasets. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： Relativity

来源：评论

学校读者我要写书评

暂无评论

Model and Feature Diversity for Bayesian Neural Networks in Mutual learning

arXiv

引用

arXiv 2024年

作者： Pham, Cuong Nguyen, Cuong C. Le, Trung Phung, Dinh Carneiro, Gustavo Do, Thanh-Toan Department of Data Science and AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia Centre for Vision Speech and Signal Processing University of Surrey United Kingdom VinAI Viet Nam

Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning can effectively enhance the performance of peer BNNs. In this paper, we propose a novel approach to improve BNNs performance through deep mutual learning. The proposed approaches aim to increase diversity in both network parameter distributions and feature distributions, promoting peer networks to acquire distinct features that capture different characteristics of the input, which enhances the effectiveness of mutual learning. Experimental results demonstrate significant improvements in the classification accuracy, negative log-likelihood, and expected calibration error when compared to traditional mutual learning for BNNs. © 2024, CC BY.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Regularized Shannon sampling formulas related to the special affine Fourier transform

arXiv

引用

arXiv 2023年

作者： Filbir, Frank Tasche, Manfred Veselovska, Anna Institute of Mathematics University of Rostock Germany Department of Mathematics Munich Data Science Institute Technical University of Munich Munich Center for Machine Learning Garching/Munich Germany

In this paper, we present new regularized Shannon sampling formulas related to the special affine Fourier transform (SAFT). These sampling formulas use localized sampling with special compactly supported window functions, namely B-spline, sinh-type, and continuous Kaiser–Bessel window functions. In contrast to the Shannon sampling series for SAFT, the regularized Shannon sampling formulas for SAFT possesses an exponential decay of the approximation error and are numerically robust in the presence of noise, if certain oversampling condition is fulfilled. Several numerical experiments illustrate the theoretical *** Codes 94A20, 42A38, 65T50 © 2023, CC BY.

关键词： Fourier transforms

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：