检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y.F. Scarlett, Jonathan Descartes Program CNRS@CREATE 138602 Singapore Department of Information Systems and Analytics School of Computing National University of Singapore 119077 Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore 119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank–Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ *** Codes 68T05 Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

DYNAMIC DEEP CONVOLUTIONAL CANDLESTICK LEARNER

arXiv

引用

arXiv 2022年

作者： Chen, Jun-Hao Tsai, Yun-Cheng Department of Computer Science and Information Engineering National Taiwan University Taiwan Department of Data Science Soochow University

Candlestick pattern is one of the most fundamental and valuable graphical tools in financial trading that supports traders observing the current market conditions to make the proper decision. This task has a long history and, most of the time, human experts. Recently, efforts have been made to automatically classify these patterns with the deep learning models. The GAF-CNN model is a well-suited way to imitate how human traders capture the candlestick pattern by integrating spatial features visually. However, with the great potential of the GAF encoding, this classification task can be extended to a more complicated object detection level. This work presents an innovative integration of modern object detection techniques and GAF time-series encoding on candlestick pattern tasks. We make crucial modifications to the representative yet straightforward YOLO version 1 model based on our time-series encoding method and the property of such data type. Powered by the deep neural networks and the unique architectural design, the proposed model performs pretty well in candlestick classification and location recognition. The results show tremendous potential in applying modern object detection techniques on time-series tasks in a real-time manner. © 2022, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes

arXiv

引用

arXiv 2024年

作者： Qiao, Dan Zhang, Kaiqi Singh, Esha Soudry, Daniel Wang, Yu-Xiang Department of Computer Science UC Santa Barbara United States Technion – Israel Institute of Technology Halıcıoğlu Data Science Institute UC San Diego United States

We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (e.g. NTK) are provably sub-optimal and benign overfitting does not happen, thus disqualifying existing theory for interpolating (0-loss, global optimal) solutions. We present a new theory of generalization for local minima that gradient descent with a constant learning rate can stably converge to. We show that gradient descent with a fixed learning rate η can only find local minima that represent smooth functions with a certain weighted first order total variation bounded by 1/η−1/2+Oe(σ+ √MSE) where σ is the label noise level, MSE is short for mean squared error against the ground truth, and Oe(·) hides a logarithmic factor. Under mild assumptions, we also prove a nearly-optimal MSE bound of Oe(n−4/5) within the strict interior of the support of the n data points. Our theoretical results are validated by extensive simulation that demonstrates large learning rate training induces sparse linear spline fits. To the best of our knowledge, we are the first to obtain generalization bound via minima stability in the non-interpolation case and the first to show ReLU NNs without regularization can achieve near-optimal rates in nonparametric regression. Copyright © 2024, The Authors. All rights reserved.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

DeepMind Trainer: Harnessing Cognitive Neural Networks on Raspberry Pi for Advanced Cognitive Enhancement Games 2

DeepMind Trainer: Harnessing Cognitive Neural Networks on Ra...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Abirami, P. Antony Joseph Rajan, D. Vivekanandan, T. Saillaja, V. Mohankumar, N. Rajmohan, M. Velammal Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Sakunthala Engineering College Vel Tech Multi Tech Dr Rangarajan Dr Department of Mathematics Tamil Nadu Chennai India SRM Institute of Science and Technology Faculty of Management Studies Tamil Nadu Kattankulathur Chennai India B.V. Raju Institute of Technology Department of Electronics and Communication Engineering Telangana India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350371314

The presentation summarizes a groundbreaking cognitive training program designed specifically for those who suffer from cognitive impairments or neurodevelopmental abnormalities. The work creates a dynamic platform for immersive and adaptable cognitive training games by combining cutting-edge Convolutional Neural Networks (CNNs) with Raspberry Pi technology. Memory, focus, and ability to think creatively are all qualities directly targeted by these games. The CNN model, trained on a broad dataset, interprets real-time user inputs, delivering quick feedback and altering game complexity depending on an individual's performance. The incorporation of Raspberry Pi guarantees a solution that is both affordable and easily accessible. The capacity of the system to redefine cognitive rehabilitation by providing a solution that is individualizable, interactive, and broadly deployable is the potential source of the system's influence. The goal of the work is to make a substantial contribution to the field, which will eventually be to the advantage of users, caregivers, and healthcare professionals and ultimately improve the cognitive well-being of those coping with cognitive issues. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Zero-Shot Coordination with Diversely Rewarded Partner Agents

Improving Zero-Shot Coordination with Diversely Rewarded Par...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Peilin Wu Zhenhua Yang Peng Yang Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Statistics and Data Science Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Zero-shot coordination studies the training of well-generalizing human-AI coordination agents in the scenario where human data is unavailable. To obtain a coordination agent generalize to unseen humans, prevailing methods generate a population of partner agents as proxy models of human partners and then train a coordination agent with these partner agents. Constructed partner agents are expected to be as diverse as possible to cover a wide range of human behaviors, preventing a distribution shift between training and testing stages. Recent works concentrate on studying effective methods of creating a group of high-reward while diverse partner agents to model unseen human partners. However, the resulting high-reward partner agents do not accurately reflect real-world situations, considering that human decisions are not always optimal and may sometimes even hinder the progression of coordination. Therefore, these studies still struggle to capture the potential characteristics of human partners. In this work, reinforcement learning (RL) and supervised learning (SL) are integrated to train a reward-conditioned policy. By conditioned on different desired rewards, a reward-conditioned policy simulates both low-reward and high-reward partners. Additionally, a reward-bucketed replay buffer and curriculum learning are applied to enhance reward diversity and boost the training of coordination agents. Experiments demonstrate that the proposed reward-conditioned policy is capable of generating agents with different rewards. Moreover, the zero-shot coordination performance of agents trained with these partners surpasses previous methods in the majority of scenarios within the Overcooked human-AI coordination benchmark.

关键词： Training Impedance matching Supervised learning Neural networks Reinforcement learning Benchmark testing Trajectory

来源：评论

学校读者我要写书评

暂无评论

MLOps: A Review

arXiv

引用

arXiv 2023年

作者： Wazir, Samar Kashyap, Gautam Siddharth Saxena, Parag Department of Computer Science and Engineering SEST Jamia Hamdard New Delhi India School of Data Science University of North Carolina Charlotte United States

Recently, Machine Learning (ML) has become a widely accepted method for significant progress that is rapidly evolving. Since it employs computational methods to teach machines and produce acceptable answers. The significance of the Machine Learning Operations (MLOps) methods, which can provide acceptable answers for such problems, is examined in this study. To assist in the creation of software that is simple to use, the authors research MLOps methods. To choose the best tool structure for certain projects, the authors also assess the features and operability of various MLOps methods. A total of 22 papers were assessed that attempted to apply the MLOps idea. Finally, the authors admit the scarcity of fully effective MLOps methods based on which advancements can self-regulate by limiting human engagement. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Harmony in the Australian Domain Space

arXiv

引用

arXiv 2024年

作者： Gong, Xian McCarthy, Paul X. Rizoiu, Marian-Andrei Boldi, Paolo University of Technology Sydney Sydney Australia The Data Science Institute University of New South Wales Sydney Australia Computer Science Department Università degli Studi di Milano Milan Italy

In this paper we use for the first time a systematic approach in the study of harmonic centrality at a Web domain level, and gather a number of significant new findings about the Australian web. In particular, we explore the relationship between economic diversity at the firm level and the structure of the Web within the Australian domain space, using harmonic centrality as the main structural feature. The distribution of harmonic centrality values is analyzed over time, and we find that the distributions exhibit a consistent pattern across the different years. The observed distribution is well captured by a partition of the domain space into six clusters;the temporal movement of domain names across these six positions yields insights into the Australian Domain Space and exhibits correlations with other non-structural characteristics. From a more global perspective, we find a significant correlation between the median harmonic centrality of all domains in each OECD country and one measure of global trust, the WJP Rule of Law Index. Further investigation demonstrates that 35 countries in OECD share similar harmonic centrality distributions. The observed homogeneity in distribution presents a compelling avenue for exploration, potentially unveiling critical corporate, regional, or national insights. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Machine Learning Based data Auditing Scheme for Cloud Users

An Efficient Machine Learning Based Data Auditing Scheme for...

引用

Computational Intelligence, Networks and Security (ICCINS), International Conference on

作者： A. Vamshi R. Eswari X. I. Nirmal Joel A. Divine Regan Department of Computer Applications National Institute of Technology Tiruchirappalli India Department of Data Science St. Joseph's College Tiruchirappalli India

With the wide spread of the digital world, IoT devices generate huge amounts of data and store it in cloud servers as they have less storage space. When data is outsourced to the cloud servers, IoT device users lose control of it, which means the confidentiality and integrity of the data can be compromised. Further, several Third-Party Auditors (TPAs) are available to check the integrity of the data. But most of the TPAs are based on trust. In some cases, TPAs are being hired by Cloud data centers and in some cases, the TPAs may have direct connection with data consumers. In both the cases, there is a bias and the data may be at high risk. Therefore, to overcome the trust issue, in this paper an Efficient Machine Learning based data Auditing Scheme for Cloud Users is proposed using a hybrid recommendation system. A repository is maintained which keeps track of all TPA's history. The user submits auditing request to the repository which will run the recommendation system to select appropriate TPA to check the integrity of the user data in the cloud. It chooses the best TPA and gives the auditing results to the user. The proposed scheme reduces the risk of user data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Cultivation: Transforming Agriculture for a Smart and Sustainable Future

Artificial Intelligence Cultivation: Transforming Agricultur...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Bhushan Fulkar Samir Mendhe Pawan Patil Department of Artificial Intelligence and Data science Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India Computer Science and Design Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India Artificial Intelligence and Data science Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India

The growing global population is posing unprecedented challenges for the agriculture industry, requiring it to produce more food while also addressing resource constraints and environmental concerns. Artificial intelligence (AI) has changed the game in agriculture by offering creative solutions to increase productivity, optimize resource use, and promote sustainability. Artificial intelligence (AI) has been used in the agriculture sector more and more recently. A few of the problems the industry faces in attempting to maximize its produce are improper soil treatment, disease and pest infestation, the use of driverless tractors, big data requirements, and the knowledge gap between farmers and technology. This work provides an overview of the applications of artificial intelligence in crop, weed, and disease management. The proposed work aims to review various AI techniques, including artificial neural networks (ANN) and fuzzy logic (FL).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Elevating Ocular Diagnosis: Harnessing the Power of EfficientNet for Eye Disease Classification

Elevating Ocular Diagnosis: Harnessing the Power of Efficien...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Vankadari Mohith Kalpana Raja I. R. Oviya Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven USA

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

In response to the evolving landscape of healthcare technology this study addresses the need for automated diagnostic tools in the field of ophthalmology. By utilizing deep learning methods specifically leveraging the EfficientNetV2S framework we achieve an overall accuracy rate of 94.6% in classifying images depicting common eye conditions like cataract, diabetic retinopathy, glaucoma, and normal cases. Our model exhibits capabilities across a diverse spectrum of medical conditions due to meticulous preprocessing and fine-tuning procedures. The results highlight the potential for automated technology integration in healthcare settings, which might improve patient care and treatment plans. This paper highlights the use of advanced neural network designs in the diagnosis of ocular illnesses, offering insights at the nexus of learning and medical image processing.

关键词： Glaucoma Deep learning Diabetic retinopathy Accuracy Computational modeling Neural networks Medical treatment

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：