检索结果-内蒙古大学图书馆

3rd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2024

作者： Manju Bala, P. Priyadharshini, S. Usharani, S. Balachandar, A. IFET College of Engineering An Autonomous Institution Department of Artificial Intelligence and Data Science India IFET College of Engineering An Autonomous Institution Department of Computer Science and Engineering India IFET College of Engineering An Autonomous Institution Department of Artificial Intelligence and Machine Learning India

ISBN: (纸本)9798350391565

Breast cancer is a serious worldwide health concern, and advanced diagnostic tools are needed for an accurate and timely identification of the illness. In order to classify breast cancer through ultrasound pictures, this method suggests a hybrid strategy that combines Convolutional Neural Networks (CNNs) with Recurrent Neural Networks (RNNs). CNN integration makes it possible to extract spatial data from ultrasound pictures and identify complex patterns that may be signs of cancer. Concurrently, RNNs are used to record temporal relationships between successive ultrasound frames, which enables the model to identify changing features of possible anomalies. By combining the advantages of both CNNs & RNNs, the suggested hybrid architecture improves the model's capacity to identify minute, dynamic patterns that are essential for precise diagnosis. In comparison to standalone CNN or RNN models, the hybrid model performs better in classification, as evidenced by experimental assessments carried out on a variety of ultrasound picture datasets. The findings highlight the hybrid approach's potential to improve breast cancer diagnostic skills and present a viable path for raising the precision and dependability of ultrasound-based tumour classification techniques. © 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

Tropical Cyclone Detection and Tracking Using YOLOv8 Algorithm 1

Tropical Cyclone Detection and Tracking Using YOLOv8 Algorit...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Rout, Saroja Kumar Kumar, Kottu Santosh Sahu, Ruchismita Barik, Shekharesh Pradhan, Samarendra Department of Information Technology Hyderabad India Department of Artificial Intelligence and Machine Learning Hyderabad India Templecity Institute of Technology and Engineering Department of Computer Science & Engineering Bhubaneswar India DRIEMS University Department of Computer Science & Engineering Cuttack India Data scientist Jayapur Cuttack India

ISBN: (纸本)9798350361780

Coastal areas around the world face a great threat from tropical cyclones, which makes timely and accurate identification essential for efficient disaster response. An enhanced method for detecting tropical cyclones is proposed in this work using the YOLOv8 (You Only Look Once version 8) object identification algorithm. Using the real-time object recognition capabilities of YOLOv8, the methodology is designed to tackle the challenges associated with finding cyclonic structures in satellite data. To detect crucial features typical of tropical cyclones - like cloud formations, circular symmetry, and dynamic atmospheric fluctuations - the YOLOv8 architecture is improved. To ensure its adaptability to different climatic circumstances, the model is trained using a varied dataset of labeled satellite photos. The YOLOv8-based methodology is superior to existing methods in detecting tropical cyclones with accuracy and efficiency almost in real-time, as demonstrated by the experimental results. Because of the algorithm's excellent precision, recall, and computing economy, early warning systems and catastrophe preparedness can benefit greatly from it. This research contributes to the ongoing effort to develop detection approaches for increased resilience in vulnerable coastal areas, while also utilizing YOLOv8's capabilities to address the global threat posed by tropical cyclones. This study can help clarify the necessity of improving models and conducting better observations of Tropical Cyclones. © 2024 IEEE.

关键词： Object detection

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 38

Structured Multi-Track Accompaniment Arrangement via Style P...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

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. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Asymptotic and compound e-values: multiple testing and empirical Bayes

arXiv

引用

arXiv 2024年

作者： Ignatiadis, Nikolaos Wang, Ruodu Ramdas, Aaditya Department of Statistics and Data Science Institute University of Chicago United States Department of Statistics and Actuarial Science University of Waterloo Canada Departments of Statistics & Machine Learning Carnegie Mellon University United States

We explicitly define the notions of (exact, approximate or asymptotic) compound p-values and e-values, which have been implicitly presented and extensively used in the recent multiple testing literature. While it is known that the e-BH procedure with compound e-values controls the FDR, we show the converse: every FDR controlling procedure can be recovered by instantiating the e-BH procedure with certain compound e-values. Since compound e-values are closed under averaging, this allows for combination and derandomization of FDR procedures. We then connect compound e-values to empirical Bayes. In particular, we use the fundamental theorem of compound decision theory to derive the log-optimal simple separable compound e-value for testing a set of point nulls against point alternatives: it is a ratio of mixture likelihoods. We extend universal inference to the compound setting. As one example, we construct approximate compound e-values for multiple t-tests, where the (nuisance) variances may be different across hypotheses. Finally, we provide connections to related notions in the literature stated in terms of p-values. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision theory

来源：评论

学校读者我要写书评

暂无评论

Time-Uniform Confidence Spheres for Means of Random Vectors

arXiv

引用

arXiv 2023年

作者： Chugg, Ben Wang, Hongjian Ramdas, Aaditya Machine Learning Department United States Department of Statistics and Data Science Carnegie Mellon University United States

We study sequential mean estimation in d. In particular, we derive time-uniform confidence spheres—confidence sphere sequences (CSSs)—which contain the mean of random vectors with high probability simultaneously across all sample sizes. Our results include a dimension-free CSS for log-concave random vectors, a dimension-free CSS for sub-Gaussian random vectors, and CSSs for sub-ψ random vectors (which includes sub-gamma, sub-Poisson, and sub-exponential distributions). Many of our results are optimal. For sub-Gaussian distributions we also provide a CSS which tracks a time-varying mean, generalizing Robbins’ mixture approach to the multivariate setting. Finally, we provide several CSSs for heavy-tailed random vectors (two moments only). Our bounds hold under a martingale assumption on the mean and do not require that the observations be iid. Our work is based on PAC-Bayesian theory and inspired by an approach of Catoni and Giulini. © 2023, CC BY.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

A unified recipe for deriving (time-uniform) PAC-Bayes bounds

arXiv

引用

arXiv 2023年

作者： Chugg, Ben Wang, Hongjian Ramdas, Aaditya Machine Learning Department United States Department of Statistics and Data Science Carnegie Mellon University United States

We present a unified framework for deriving PAC-Bayesian generalization bounds. Unlike most previous literature on this topic, our bounds are anytime-valid (i.e., time-uniform), meaning that they hold at all stopping times, not only for a fixed sample size. Our approach combines four tools in the following order: (a) nonnegative supermartingales or reverse submartingales, (b) the method of mixtures, (c) the Donsker-Varadhan formula (or other convex duality principles), and (d) Ville's inequality. Our main result is a PAC-Bayes theorem which holds for a wide class of discrete stochastic processes. We show how this result implies time-uniform versions of wellknown classical PAC-Bayes bounds, such as those of Seeger, McAllester, Maurer, and Catoni, in addition to many recent bounds. We also present several novel bounds. Our framework also enables us to relax traditional assumptions;in particular, we consider nonstationary loss functions and non-i.i.d. data. In sum, we unify the derivation of past bounds and ease the search for future bounds: one may simply check if our supermartingale or submartingale conditions are met and, if so, be guaranteed a (time-uniform) PAC-Bayes bound. Copyright © 2023, The Authors. All rights reserved.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Low-rank optimal transport through factor relaxation with latent coupling 24

Low-rank optimal transport through factor relaxation with la...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Peter Halmos Xinhao Liu Julian Gold Benjamin J. Raphael Department of Computer Science Princeton University Center for Statistics and Machine Learning Princeton University

ISBN: (纸本)9798331314385

Optimal transport (OT) is a general framework for finding a minimum-cost transport plan, or coupling, between probability distributions, and has many applications in machine learning. A key challenge in applying OT to massive datasets is the quadratic scaling of the coupling matrix with the size of the dataset. Forrow et al. (2019) introduced a factored coupling for the k-Wasserstein barycenter problem, which Scetbon et al. (2021) adapted to solve the primal low-rank OT problem. We derive an alternative parameterization of the low-rank problem based on the latent coupling (LC) factorization previously introduced by Lin et al. (2021) generalizing Forrow et al. (2019). The LC factorization has multiple advantages for low-rank OT including decoupling the problem into three OT problems and greater flexibility and interpretability. We leverage these advantages to derive a new algorithm Factor Relaxation with Latent Coupling (FRLC), which uses coordinate mirror descent to compute the LC factorization. FRLC handles multiple OT objectives (Wasserstein, Gromov-Wasserstein, Fused Gromov-Wasserstein), and marginal constraints (balanced, unbalanced, and semi-relaxed) with linear space complexity. We provide theoretical results on FRLC, and demonstrate superior performance on diverse applications - including graph clustering and spatial transcriptomics - while demonstrating its interpretability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Time Series Forecasting Models for Weather Prediction: ARIMA vs. STL 8

Comparative Analysis of Time Series Forecasting Models for W...

引用

8th IEEE International Conference on Computing, Communication, Control and Automation, ICCUBEA 2024

作者： Kamble, Aahash Belsare, Sanika Chaudhari, Purva Gourshettiwar, Palash Gundewar, Swapnil Datta Meghe Institute of Higher Education and Research Department of Artificial Intellegence and Data Science Wardha India Department of Artificial Intellegence and Data Science Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Department of Computer Science and Medical Engineering Wardha India Datta Meghe Institute of Higher Education and Research Department of Artificial Intellegence and Machine Learning Wardha India

ISBN: (纸本)9798350391770

This research compares two well-known models for predicting weather: ARIMA (Auto Regressive Integrated Moving Average) and STL (Seasonal-Trend Decomposition using Loess). Accurate weather forecasts are crucial for businesses and daily life, making strong forecasting methods necessary. ARIMA finds linear patterns and time dependencies in data, while STL splits time series into seasonal, trend, and random parts. Using real-world weather data, we train and test these models. We compare their performances using MSE (Mean Squared Error) and R2 (R-squared) metrics. The research demonstrates that the STL model performs better than the ARIMA model at accurately predicting weather patterns and fitting to the data. This superior performance makes the STL model a more dependable choice for weather forecasting. This study enhances techniques for weather prediction and offers valuable information to those making decisions in weather-sensitive businesses. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Generalized equivalences between subsampling and ridge regularization 23

Generalized equivalences between subsampling and ridge regul...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Pratik Patil Jin-Hong Du Department of Statistics University of California Berkeley CA Department of Statistics and Data Science & Machine Learning Department Carnegie Mellon University Pittsburgh PA

We establish precise structural and risk equivalences between subsampling and ridge regularization for ensemble ridge estimators. Specifically, we prove that linear and quadratic functionals of subsample ridge estimators, when fitted with different ridge regularization levels λ and subsample aspect ratios ψ, are asymptotically equivalent along specific paths in the (λ, ψ)-plane (where ψ is the ratio of the feature dimension to the subsample size). Our results only require bounded moment assumptions on feature and response distributions and allow for arbitrary joint distributions. Furthermore, we provide a data-dependent method to determine the equivalent paths of (λ, ψ). An indirect implication of our equivalences is that optimally tuned ridge regression exhibits a monotonic prediction risk in the data aspect ratio. This resolves a recent open problem raised by Nakkiran et al. [1] for general data distributions under proportional asymptotics, assuming a mild regularity condition that maintains regression hardness through linearized signal-to-noise ratios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimized Automated Stock Trading using DQN and Double DQN

Optimized Automated Stock Trading using DQN and Double DQN

引用

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

作者： Gurudutt S Bharadwaj David Pratap Narayana Darapaneni Department of Computer Science PES University Bengaluru India Department of Data Science and Machine Learning Great Learning Bengaluru India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

Stock Portfolio management involves managing the buying, holding and selling decisions for the various stocks in the portfolio. There has been work where Reinforcement learning (RL) based actor-critic methods like Deep Direct Policy Gradient (DDPG) have been used for asset allocation problems. Here an attempt has been made to use solely critic-based value function methods like Deep Q-network (DQN) and Double DQN for estimating Q-values of market actions. Then, an optimized portfolio management algorithm designed to balance trades across a basket of stocks is designed. Five stocks are chosen of different price ranges from NYSE and NASDAQ stock exchanges. The average cumulative percentage returns provided by DQN was 55% on testing data with an average Maximum Drawdown (MDD) of 2.5%. The same with Double DQN was 71% on testing data with an average MDD of 2.83%. These results were significantly better than the case when a traditional Buy and Hold strategy was to be employed.

关键词： Reinforcement learning Resource management Stock markets Portfolios Computational intelligence Testing

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：