检索结果-内蒙古大学图书馆

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

学校读者我要写书评

暂无评论

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：

Sampling Strategies for Compressive Imaging Under Statistical Noise

学校读者我要写书评

暂无评论

Sampling Strategies for Compressive Imaging Under Statistica...

2023 International Conference on Sampling Theory and Applications, SampTA 2023

作者： Hoppe, Frederik Krahmer, Felix Verdun, Claudio Mayrink Menzel, Marion I. Rauhut, Holger Rwth Aachen University Chair of Mathematics of Information Processing Aachen Germany Technical University of Munich Department of Mathematics Munich Germany Munich Center for Machine Learning Munich Germany Technical University of Munich Munich Data Science Institute Germany Technische Hochschule Ingolstadt AImotion Bavaria Ingolstadt Germany Technical University of Munich Department of Physics Garching Germany Ge Healthcare Munich Germany

ISBN: (纸本)9798350328851

Most of the compressive sensing literature in signal processing assumes that the noise present in the measurement has an adversarial nature, i.e., it is bounded in a certain norm. At the same time, the randomization introduced in the sampling scheme usually assumes an i.i.d. model where rows are sampled with replacement. In this case, if a sample is measured a second time, it does not add additional information. For many applications, where the statistical noise model is a more accurate one, this is not true anymore since a second noisy sample comes with an independent realization of the noise, so there is a fundamental difference between sampling with and without replacement. Therefore, a more careful analysis must be performed. In this short note, we illustrate how one can mathematically transition between these two noise models. This transition gives rise to a weighted LASSO reconstruction method for sampling without replacement, which numerically improves the solution of high-dimensional compressive imaging problems. © 2023 IEEE.

关键词： Compressed sensing

CENTRAL LIMIT THEOREMS FOR SMOOTH OPTIMAL TRANSPORT MAPS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Manole, Tudor Balakrishnan, Sivaraman Niles-Weed, Jonathan Wasserman, Larry Statistics and Data Science Center Massachusetts Institute of Technology United States Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States Center for Data Science New York University United States Courant Institute of Mathematical Sciences New York University United States

One of the central objects in the theory of optimal transport is the Brenier map: the unique monotone transformation which pushes forward an absolutely continuous probability law onto any other given law. A line of recent work has analyzed L2 convergence rates of plugin estimators of Brenier maps, which are defined as the Brenier map between density estimators of the underlying distributions. In this work, we show that such estimators satisfy a pointwise central limit theorem when the underlying laws are supported on the flat torus of dimension d ≥ 3. We also derive a negative result, showing that these estimators do not converge weakly in L2 when the dimension is sufficiently large. Our proofs hinge upon a quantitative linearization of the Monge-Ampère equation, which may be of independent interest. This result allows us to reduce our problem to that of deriving limit laws for the solution of a uniformly elliptic partial differential equation with a stochastic right-hand side, subject to periodic boundary conditions. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Zhidi Li, Ying Yin, Feng Maroñas, Juan Thiéry, Alexandre H. The Department of Statistics and Data Science National University of Singapore Singapore117546 Singapore The Department of Statistics and Actuarial Science The University of Hong Kong Hong Kong The School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen518172 China The Machine Learning Group Universidad Autónoma de Madrid The Department of Quantitative Methods CUNEF University

Gaussian process state-space models (GPSSMs) have emerged as a powerful framework for modeling dynamical systems, offering interpretable uncertainty quantification and inherent regularization. However, existing GPSSMs face significant challenges in handling high-dimensional, non-stationary systems due to computational inefficiencies, limited scalability, and restrictive stationarity assumptions. In this paper, we propose an efficient transformed Gaussian process state-space model (ETGPSSM) to address these limitations. Our approach leverages a single shared Gaussian process (GP) combined with normalizing flows and Bayesian neural networks, enabling efficient modeling of complex, high-dimensional state transitions while preserving scalability. To address the lack of closed-form expressions for the implicit process in the transformed GP, we follow its generative process and introduce an efficient variational inference algorithm, aided by the ensemble Kalman filter (EnKF), to enable computationally tractable learning and inference. Extensive empirical evaluations on synthetic and real-world datasets demonstrate the superior performance of our ETGPSSM in system dynamics learning, high-dimensional state estimation, and time-series forecasting, outperforming existing GPSSMs and neural network-based methods in both accuracy and computational efficiency. Copyright © 2025, The Authors. All rights reserved.

关键词： Scalability

Disease and Medications Text Visualization Using Scattertext

学校读者我要写书评

暂无评论

Disease and Medications Text Visualization Using Scattertext

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Rama Krishna, K. Sandhya, Kaipa Praveen Gujjar, J. Devadas, Raghavendra M. Hiremani, Vani Sapna, R. Impact college of Engineering and Applied Sciences Department of Artificial Intelligence and Machine Learning Bengaluru India Impact college of Engineering and applied sciences Department of Data Science Bengaluru India Faculty of Management Studies Bengaluru India Department of Information Technology Manipal India University Pune India

ISBN: (纸本)9798331527495

Before text data can be analysed and visualised, it must be thoroughly cleaned due to its messy nature. data visualizations use the data to tell an engaging and simple-to-read story. That is what the Scattertext tool does. Scatter text allows which terms stand out in your corpora and how their frequency varies across categories. The dataset used in this paper includes reviews of drugs. This dataset offers a useful window into how people discuss their thoughts and experiences using various drugs. The drug names, user ratings, and the actual written reviews are among the details included in the dataset. This dataset consists of drug reviews collected from various sources, hence expressing a wide range of opinions and feelings. Each row in this dataset represents the experience a user had with a given medication and hence allows us to explore those emotions that are associated with any particular set of drugs. Understanding opinion expressed in the review about drugs might go a long way in helping decision-making processes in both healthcare and pharmaceuticals. The scatter plot distinguishes between labelled points and unlabelled ones by using a custom algorithm for Scattertext. By hovering their cursor over the labelled areas done client-side, users can interactively see which terms correspond to which points. © 2025 IEEE.

关键词： data visualization

An Optimized Hybrid Deep learning and IoT-Enabled Health System in Retina Image Analysis for Blindness Detection

学校读者我要写书评

暂无评论

An Optimized Hybrid Deep Learning and IoT-Enabled Health Sys...

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： J Yamini T Kanimozhi A Jenefa K Bagyalakshmi K Aarthi P Dhivya Department of Artificial Intelligence and Machine learning Kalaignar Karunanidhi Institute of Technology Coimbatore India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore India Department of Computer Science and Engineering PPG Institute of Technology Coimbatore India Department of Mathematics SNS College of Technology Coimbatore India Department of Artificial Intelligence and Data Science Kalaignar Karunanidhi Institute of Technology Coimbatore India Department of Computer Science and Engineering Bannari Amman Institute of Technology Erode India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Early signs of blind identification and retina disorder in retina image has become prominent. Deep learning techniques are used to improve the accuracy in detecting pathological conditions from the retina images. However, the models have some challenges such as suboptimal feature extraction and inefficient filtering methods. Most of the traditional methods often result in overfitting and under fitting, thus decreasing the generalizability and robustness of the model. The proposed hybrid approach combines bilateral filtering with Convolutional Neural Networks (CNN). In this approach, bilateral filtering acts as a pre-processing technique to enhance image quality by reducing noise and preserving edges for the correct extraction of features. The CNN is applied for feature extraction and it is used to self-learn complex patterns from filtered images. The proposed approach gives an accuracy of $95.65 \%$ with a loss of 0.18 without overfitting and underfitting.

关键词： Optical filters Accuracy Filtering Noise Predictive models Retina Feature extraction Convolutional neural networks Diseases Overfitting

Predicting gastric cancer response to anti-HER2 therapy or anti-HER2 combined immunotherapy based on multimodal data

学校读者我要写书评

暂无评论

Signal Transduction and Targeted Therapy 2024年第9期9卷 4137-4148页

作者： Zifan Chen Yang Chen Yu Sun Lei Tang Li Zhang Yajie Hu Meng He Zhiwei Li Siyuan Cheng Jiajia Yuan Zhenghang Wang Yakun Wang Jie Zhao Jifang Gong Liying Zhao Baoshan Cao Guoxin Li Xiaotian Zhang Bin Dong Lin Shen Center for Data Science Peking UniversityBeijingChina Department of Gastrointestinal Oncology Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education)Peking University Cancer Hospital and InstituteBeijingChina Department of Pathology Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education)Peking University Cancer Hospital and InstituteBeijingChina Department of Radiology Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education)Peking University Cancer Hospital and InstituteBeijingChina National Biomedical Imaging Center Peking UniversityBeijingChina Department of General Surgery Nanfang HospitalSouthern Medical UniversityGuangzhouChina Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor GuangzhouChina Department of Medical Oncology and Radiation Sickness Peking University Third HospitalBeijingChina National Engineering Laboratory for Big Data Analysis and Applications Peking UniversityBeijingChina Beijing International Center for Mathematical Research(BICMR) Peking UniversityBeijingChina Center for Machine Learning Research Peking UniversityBeijingChina

The sole use of single modality data often fails to capture the complex heterogeneity among patients,including the variability in resistance to anti-HER2 therapy and outcomes of combined treatment regimens,for the treatment of HER2-positive gastric cancer(GC).This modality deficit has not been fully considered in many ***,the application of artificial intelligence in predicting the treatment response,particularly in complex diseases such as GC,is still in its ***,this study aimed to use a comprehensive analytic approach to accurately predict treatment responses to anti-HER2 therapy or anti-HER2 combined immunotherapy in patients with HER2-positive *** collected multi-modal data,comprising radiology,pathology,and clinical information from a cohort of 429 patients:310 treated with anti-HER2 therapy and 119 treated with a combination of anti-HER2 and anti-PD-1/PD-L1 inhibitors *** introduced a deep learning model,called the Multi-Modal model(MuMo),that integrates these data to make precise treatment response *** achieved an area under the curve score of 0.821 for anti-HER2 therapy and 0.914 for combined ***,patients classified as low-risk by MuMo exhibited significantly prolonged progression-free survival and overall survival(log-rank test,P<0.05).These findings not only highlight the significance of multi-modal data analysis in enhancing treatment evaluation and personalized medicine for HER2-positive gastric cancer,but also the potential and clinical value of our model.

关键词： immunotherapy HER2 cancer

Stock Market Forecasting Using LSTM

学校读者我要写书评

暂无评论

Stock Market Forecasting Using LSTM

Communication & Computing (WCONF), World Conference on

作者： J. Aswini Dinesh S C. Lakshmipriya Lokesh Krishnaa M Siva Subramanian R Dept of Artificial Intelligence & Machine Learning Saveetha Engineering College(Autonomous) Department of Artificial Intelligence and Data Science Saveetha Engineering College(Autonomous) Department CSE S.A. Engineering College Department CSE R.M.K College of Engineering and Technology

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

In this research paper, a novel methodology for forecasting stock market trends is presented: the utilization of Long Short-Term Memory networks, which are a part of RNN network. This model effectively incorporates the delivery of dynamic datasets, model training, and the immediate distribution of the learned TensorFlow model through the utilization of deep learning. The Long Short-Term Memory is a highly effective tool for understanding complex stock market behaviors, as it captures sequential dependencies and effortlessly adapts to changing market conditions. Transparency, collaboration, scalability, user experience, and security are given top priority in the project to guarantee accessibility for users of all levels of expertise. By outperforming conventional neural network architecture in prediction and by capturing dependencies over extended time periods, the LSTM model demonstrates its value. This research may pave the way for additional financial forecasting applications, thereby enhancing the efficacy of decision-making instruments in dynamic stock market environments.

关键词： Deep learning Training Adaptation models Decision making Computer architecture Predictive models User experience Stock markets Forecasting Long short term memory

TOPOGRAPH: AN EFFICIENT GRAPH-BASED FRAMEWORK FOR STRICTLY TOPOLOGY PRESERVING IMAGE SEGMENTATION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lux, Laurin Berger, Alexander H. Weers, Alexander Stucki, Nico Rueckert, Daniel Bauer, Ulrich Paetzold, Johannes C. School of Computation Information and Technology Technical University of Munich Germany Department of Computing Imperial College London United Kingdom Munich Center for Machine Learning Germany Munich Data Science Institute Technical University of Munich Munich Germany

Topological correctness plays a critical role in many image segmentation tasks, yet most networks are trained using pixel-wise loss functions, such as Dice, neglecting topological accuracy. Existing topology-aware methods often lack robust topological guarantees, are limited to specific use cases, or impose high computational costs. In this work, we propose a novel, graph-based framework for topologically accurate image segmentation that is both computationally efficient and generally applicable. Our method constructs a component graph that fully encodes the topological information of both the prediction and ground truth, allowing us to efficiently identify topologically critical regions and aggregate a loss based on local neighborhood information. Furthermore, we introduce a strict topological metric capturing the homotopy equivalence between the union and intersection of prediction-label pairs. We formally prove the topological guarantees of our approach and empirically validate its effectiveness on binary and multi-class datasets. Our loss demonstrates state-of-the-art performance with up to fivefold faster loss computation compared to persistent homology methods. © 2024, CC BY.

关键词： Image segmentation