检索结果-内蒙古大学图书馆

15th International Conference on Intelligent Computing, ICIC 2019

作者： Jiao, Zhihao Zhang, Lijun Yuan, Chang-An Qin, Xiao Shang, Li Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Collaborative Innovation Center of Intelligent New Energy Vehicle Shanghai China School of Automotive Studies Tongji University Shanghai China Science Computing and Intelligent Information Processing of GuangXi Higher Education Key Laboratory Nanning Normal University NanningGuangxi China Department of Communication Technology College of Electronic Information Engineering Suzhou Vocational University SuzhouJiangsu215104 China

ISBN: (纸本)9783030267629

Plants play an important role in human life, Identifying and protecting plants has far-reaching implications for the sustainable development of the ecological environment. Plant leaves can often reflect important characteristics of plants, so it is scientific and feasible to effectively identify plant species through plant leaves. With the rapid development of deep learning in recent years, it has been widely applied in plant leaf recognition. Compared with the traditional method, deep learning based plant leaf recognition algorithm can extract plant leaf features more effectively and can greatly improve the performance. Based on the detailed analysis of the structural characteristics of three classical convolutional neural network models, this paper comprehensively compares the recognition performance of three convolutional neural network models on ICL plant leaf datasets. The experimental results show that the Conditional Generative Adversarial Net with optimized output layer has better recognition results on the plant leaf dataset than other convolutional neural network models. © 2019, Springer Nature Switzerland AG.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Emerging Intelligent Computing Technology and Applications 1

引用

丛书名： Communications in Computer and information Science

1000年

作者： De-Shuang Huang Phalguni Gupta Xiang Zhang Prashan Premaratne

ISBN: (数字)9783642318375

ISBN: (纸本)9783642318368

This book constitutes the refereed proceedings of the 8th International Conference on Intelligent Computing, ICIC 2012, held in Huangshan, China, in July 2012. The 242 revised full papers presented in the three volumes LNCS 7389, LNAI 7390, and CCIS 304 were carefully reviewed and selected from 753 submissions. The papers in this volume (CCIS 304) are organized in topical sections on Neural Networks; Particle Swarm Optimization and Niche Technology; Kernel Methods and Supporting Vector machines; Biology Inspired Computing and Optimization; Knowledge Discovery and Data Mining; Intelligent Computing in Bioinformatics; Intelligent Computing in Pattern Recognition; Intelligent Computing in Image Processing; Intelligent Computing in Computer Vision; Intelligent Control and Automation; Knowledge Representation/Reasoning and Expert systems; Advances in information Security; Protein and Gene Bioinformatics; Soft Computing and Bio-Inspired Techiques in Real-World Applications; Bio-Inspired Computing and Applications.

关键词： Artificial Intelligence Algorithm Analysis and Problem Complexity information systems Applications (incl. Internet) Computation by Abstract Devices Pattern Recognition Computer Communication Networks

来源：评论

学校读者我要写书评

暂无评论

Dual-energy X-ray images enhancement based on a discrete wavelet transform fusion technique for luggage inspection at airport

Dual-energy X-ray images enhancement based on a discrete wav...

引用

International Conference on Image and Signal Processing and their Applications (ISPA)

作者： Mohamed CHOUAI Mostafa MERAH José-Luis SANCHO-GOMEZ Malika MIMI Signals and systems laboratory Mostaganem University Mostaganem Algeria TDAM Research Group (Data Processing and Machine Learning) Information and Communications Universidad Politécnica de Cartagena Cartagena Murcia Spain

ISBN: (纸本)9781728131573

Billions of suitcases and other belongings are checked every year in airport X-ray systems around the world. This process is very important because it involves the detection of potentially dangerous objects such as firearms and explosives. However, the image quality of x-ray screening devices needed to be improved. This article attempts to make a contribution to the field of improving the radiographic image of luggage by proposing a complete procedure for improving the image quality based on discrete wavelet transform (DWT) image fusion followed by a noise suppression operation to obtain a good improvement of the fusion result. This article also presents a comparative analysis of five well-known image enhancement algorithm models, the evaluation is done using the Peak Signal-to-Noise Ratio (PSNR). The results show that the proposed system provides promising results compared to the other techniques tested, which proves that the proposed approach is very appropriate and recommended for easy / fast identification of threatening objects in a manual or automatic manner.

关键词： Transport security Baggage control Image enhancement Fusion Wavelet transform Fusion reactions image enhancement Fusion, biological Image quality wavelet transforms Airports FUSION fusion (melting) discrete wavelet transform image enhancement algorithm Peak signal-to-noise ratio Firearms double energy

来源：评论

学校读者我要写书评

暂无评论

Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent 37

Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Sto...

引用

37th Conference on Neural information Processing systems, NeurIPS 2023

作者： Zhu, Lingjiong Gürbüzbalaban, Mert Raj, Anant Şimşekli, Umut Dept. of Mathematics Florida State University United States Dept. of Management Science and Information Systems Rutgers Business School United States Center for Statistics and Machine Learning Princeton University United States Coordinated Science Laboratory University of Illinois Urbana-Champaign United States Inria Paris CNRS Ecole Normale Supérieure PSL Research University France

ISBN: (纸本)9781713899921

Algorithmic stability is an important notion that has proven powerful for deriving generalization bounds for practical algorithms. The last decade has witnessed an increasing number of stability bounds for different algorithms applied on different classes of loss functions. While these bounds have illuminated various properties of optimization algorithms, the analysis of each case typically required a different proof technique with significantly different mathematical tools. In this study, we make a novel connection between learning theory and applied probability and introduce a unified guideline for proving Wasserstein stability bounds for stochastic optimization algorithms. We illustrate our approach on stochastic gradient descent (SGD) and we obtain time-uniform stability bounds (i.e., the bound does not increase with the number of iterations) for strongly convex losses and non-convex losses with additive noise, where we recover similar results to the prior art or extend them to more general cases by using a single proof technique. Our approach is flexible and can be generalizable to other popular optimizers, as it mainly requires developing Lyapunov functions, which are often readily available in the literature. It also illustrates that ergodicity is an important component for obtaining time-uniform bounds - which might not be achieved for convex or non-convex losses unless additional noise is injected to the iterates. Finally, we slightly stretch our analysis technique and prove time-uniform bounds for SGD under convex and non-convex losses (without additional additive noise), which, to our knowledge, is novel. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

RIDNet: Recursive information Distillation Network for Color Image Denoising

RIDNet: Recursive Information Distillation Network for Color...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Shengkai Zhuo Zhi Jin Wenbin Zou Xia Li Shenzhen University China College of Electronics and Information Engineering Shenzhen Key Laboratory of Advanced Machine Learning and Applications Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University School of Intelligent Systems Engineering Sun Yat-sen University Sun Yat-sen University China

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Color image denoising is more challenging in effectiveness when compared with the grayscale one. Most existing methods play a certain role in efficiency or flexibility, but lack robustness to handle various noise levels, especially the severe noise. This keeps them away from being practically applied to color image denoising. To address this issue, we propose a robust CNN based denoiser, namely Recursive information Distillation Network (RIDNet), to handle the denoising task at high noise levels. The proposed RIDNet simultaneously keeps the efficiency and flexibility by introducing the information distillation module and merging a tunable noise level map as the input, respectively. Experiment results on Additive White Gaussian Noise (AWGN) images demonstrate that our method outperforms most of the state-of-the-art color image denoisers.

关键词： Noise reduction Noise level Color Training AWGN Noise measurement Task analysis

来源：评论

学校读者我要写书评

暂无评论

Applying recurrence time entropy to identify changes in event-related potentials

引用

The European Physical Journal Special Topics 2022年第1期232卷 161-168页

作者： Frolov, Nikita Pitsik, Elena Maksimenko, Vladimir Hramov, Alexander Laboratory of Dynamics in Biological Systems KU Leuven Leuven Belgium Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia Neuroscience and Cognitive Technology Laboratory Innopolis University Innopolis Russia Institute of Information Technology Mathematics and Mechanics Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia

The event-related potentials (ERPs) are an essential response of the human brain to environmental changes that correlate with behavior. They are thus widely used as indicators of brain activity in fundamental research and response sources in brain communication devices. The problem of their robust identification from single-trial EEG recordings or limited data sets is timely and challenging. The current study addresses this issue by evaluating the ERP-associated variations of EEG signals using the measures of complexity based on the recurrence quantification analysis (RQA). Specifically, we demonstrate that the recurrence time entropy (RTE) is a good indicator of ERP-associated changes in the course of successive discrimination of ambiguous visual stimuli. Using the distribution of recurrence times, we conclude why exactly this measure is sensitive to ERP-associated variations of EEG signal.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting Atmospheric Regimes using Cross-Validated Clustering 3

Detecting Atmospheric Regimes using Cross-Validated Clusteri...

引用

3rd International Conference on Knowledge Discovery and Data Mining, KDD 1997

作者： Smyth, Padhraic Ghil, Michael Ide, Kayo Roden, Joe Fraser, Andrew Information and Computer Science University of California IrvineCA92697-3425 United States Department of Atmospheric Sciences Inst. of Geophysics and Planetary Physics University of California Los Angeles Los AngelesCA90024-1565 United States Machine Learning Systems Group Jet Propulsion Laboratory 525-3660 PasadenaCA91109-8099 United States Systems Science Portland State University PortlandOR97207-0751 United States The Jet Propulsion Laboratory 525-3660 California Institute of Technology PasadenaCA91109 United States

ISBN: (纸本)1577350278

Low-frequency variability in geopotential height records of the Northern Hemisphere is a topic of significance in atmospheric science, having profound implications for climate modeling and prediction. A debate has existed in the atmospheric science literature as to whether or not "regimes"or clusters exist in geopotential heights, and if so, how many such clusters. This paper tells the "detective story"of how cross-validated mixture model clustering, a methodology originally described at the 1996 KDD conference (Smyth, 1996), has recently provided clear and objective evidence that three clusters exist in the Northern Hemisphere, where each of the detected clusters has a direct physical interpretation. Cross-validated mixture modeling has thus answered an important open scientific question. Copyright © 1997, American Association for Artificial Intelligence (***). All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

On the generalization of stochastic gradient descent with momentum

The Journal of Machine Learning Research

引用

The Journal of machine learning Research 2024年第1期25卷 1132-1187页

作者： Ali Ramezani-Kebrya Kimon Antonakopoulos Volkan Cevher Ashish Khisti Ben Liang Department of Informatics University of Oslo and Visual Intelligence Centre Integreat Norwegian Centre for Knowledge-driven Machine Learning Oslo Norway Laboratory for Information and Inference Systems (LIONS) EPFL EPFL STI IEL LIONS Lausanne Switzerland Department of Electrical and Computer Engineering University of Toronto Toronto ON Canada

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that there exists a convex loss function for which the stability gap for multiple epochs of SGD with standard heavy-ball momentum (SGDM) becomes unbounded. Then, for smooth Lipschitz loss functions, we analyze a profiles momentum-based update rule, i.e., SGD with early momentum (SGDEM) under a broad range of step-sizes, and show that it can train machine learning models for multiple epochs with a guarantee for generalization. Finally, for the special case of strongly convex loss functions, we find a range of momentum such that multiple epochs of standard SGDM, as a special form of SGDEM, also generalizes. Extending our results on generalization, we also develop an upper bound on the expected true risk, in terms of the number of training steps, sample size, and momentum. Our experimental evaluations verify the consistency between the numerical results and our theoretical bounds. SGDEM improves the generalization error of SGDM when training ResNet-18 on ImageNet in practical distributed settings.

关键词： uniform stability generalization error heavy-ball momentum stochastic gradient descent non-convex

来源：评论

学校读者我要写书评

暂无评论

Change-Point Detection in Industrial Data Streams based on Online Dynamic Mode Decomposition with Control

arXiv

引用

arXiv 2024年

作者： Wadinger, Marek Kvasnica, Michal Kawahara, Yoshinobu Institute of Information Engineering Automation and Mathematics Slovak University of Technology in Bratislava Radlinskeho 9 Bratislava812 37 Slovakia Machine Learning & Systems Laboratory Osaka University 1–5 Yamadaoka Osaka Suita565–0871 Japan

We propose a novel change-point detection method based on online Dynamic Mode Decomposition with control (ODMDwC). Leveraging ODMDwC’s ability to find and track linear approximation of a non-linear system while incorporating control effects, the proposed method dynamically adapts to its changing behavior due to aging and seasonality. This approach enables the detection of changes in spatial, temporal, and spectral patterns, providing a robust solution that preserves correspondence between the score and the extent of change in the system dynamics. We formulate a truncated version of ODMDwC and utilize higher-order time-delay embeddings to mitigate noise and extract broad-band features. Our method addresses the challenges faced in industrial settings where safety-critical systems generate non-uniform data streams while requiring timely and accurate change-point detection to protect profit and life. Our results demonstrate that this method yields intuitive and improved detection results compared to the Singular-Value-Decomposition-based method. We validate our approach using synthetic and real-world data, showing its competitiveness to other approaches on complex systems’ benchmark datasets. Provided guidelines for hyperparameters selection enhance our method’s practical applicability. © 2024, CC BY.

关键词： Dynamic mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Plant Leaf Recognition Network Based on Feature learning and Metric learning 16th

Plant Leaf Recognition Network Based on Feature Learning and...

引用

16th International Conference on Intelligent Computing, ICIC 2020

作者： Yang, Hongwei Wu, Di Yuan, Changan Qin, Xiao Wu, Hongjie Zhao, Xingming Zhao, Zhongqiu Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Guangxi Academy of Science Nanning530025 China School of Computer and Information Engineering Nanning Normal University Nanning530299 China School of Computer Science and Technology Soochow University Suzhou215006 China School of Electronic and Information Engineering Suzhou University of Science and Technology Suzhou215009 China Fudan University Shanghai200433 China Key Laboratory of Computational Neuro-Science and Brain-Inspired Intelligence Ministry of Education Shanghai China College of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

ISBN: (纸本)9783030607982

Plant image recognition is an important thing for protecting plants, protecting the environment, and protecting nature. Recently, most models in the field of plant leaf recognition make classification after extracting global features. In this paper, we propose a plant leaf recognition model based on metric learning. Metric learning calculates the similarity of the extracted feature vectors to obtain the distance between different sample features, so as to determine whether similar pictures belong to the same category, and then achieve the classification effect. In this study, feature triplet are used for metric learning, and the loss function we used is triplet-loss. © 2020, Springer Nature Switzerland AG.

关键词： Image recognition

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：