检索结果-内蒙古大学图书馆

33rd conference on Neural Information processing Systems (NeurIPS)

作者： Lang, Hunter Zhang, Pengchuan Xiao, Lin Microsoft Res AI Redmond WA 98052 USA

Despite the development of numerous adaptive optimizers, tuning the learning rate of stochastic gradient methods remains a major roadblock to obtaining good practical performance in machine learning. Rather than changing the learning rate at each iteration, we propose an approach that automates the most common hand-tuning heuristic: use a constant learning rate until "progress stops", then drop. We design an explicit statistical test that determines when the dynamics of stochastic gradient descent reach a stationary distribution. This test can be performed easily during training, and when it fires, we decrease the learning rate by a constant multiplicative factor. Our experiments on several deep learning tasks demonstrate that this statistical adaptive stochastic approximation (SASA) method can automatically find good learning rate schedules and match the performance of hand-tuned methods using default settings of its parameters. The statistical testing helps to control the variance of this procedure and improves its robustness.

关键词： statistical tests

来源：评论

学校读者我要写书评

暂无评论

THE LIMITATION AND PRACTICAL ACCELERATION OF stochastic GRADIENT ALGORITHMS IN INVERSE PROBLEMS 44

THE LIMITATION AND PRACTICAL ACCELERATION OF STOCHASTIC GRAD...

引用

44th IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Tang, Junqi Egiazarian, Karen Davies, Mike Univ Edinburgh Sch Engn Edinburgh Midlothian Scotland Noiseless Imaging Ltd Tampere Finland Tampere Univ Fac Comp & Elect Engn Tampere Finland

ISBN: (纸本)9781479981311

In this work we investigate the practicability of stochastic gradient descent and recently introduced variants with variance-reduction techniques in imaging inverse problems, such as space-varying image deblurring. Such algorithms have been shown in machine learning literature to have optimal complexities in theory, and provide great improvement empirically over the full gradient methods. Surprisingly, in some tasks such as image deblurring, many of such methods fail to converge faster than the accelerated full gradient method (FISTA), even in terms of epoch counts. We investigate this phenomenon and propose a theory-inspired mechanism to characterize whether a given inverse problem should be preferred to be solved by stochastic optimization technique with a known sampling pattern. Furthermore, to overcome another key bottleneck of stochastic optimization which is the heavy computation of proximal operators while maintaining fast convergence, we propose an accelerated primal-dual SGD algorithm and demonstrate the effectiveness of our approach in image deblurring experiments.

关键词： stochastic Optimization Inverse Problems image processing

来源：评论

学校读者我要写书评

暂无评论

Deep Bayesian Data Mining 20

Deep Bayesian Data Mining

引用

13th Annual ACM International conference on Web Search and Data Mining (WSDM)

作者： Chien, Jen-Tzung Natl Chiao Tung Univ Hsinchu Taiwan

ISBN: (纸本)9781450368223

This tutorial addresses the fundamentals and advances in deep Bayesian mining and learning for natural language with ubiquitous applications ranging from speech recognition [7, 55] to document summarization [8], text classification [5, 75], text segmentation [18], information extraction [50], image caption generation [69, 72], sentence generation [25, 46], dialogue control [22, 76], sentiment classification, recommendation system, question answering [58] and machine translation [2], to name a few. Traditionally, "deep learning" is taken to be a learning process where the inference or optimization is based on the real-valued deterministic model. The "semantic structure" in words, sentences, entities, actions and documents drawn from a large vocabulary may not be well expressed or correctly optimized in mathematical logic or computer programs. The "distribution function" in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated. This tutorial addresses the fundamentals of statistical models and neural networks, and focus on a series of advanced Bayesian models and deep models including hierarchical Dirichlet process [61], Chinese restaurant process [4], hierarchical Pitman-Yor process [60], Indian buffet process [35], recurrent neural network (RNN) [26, 41, 48, 65], long short-term memory, sequence-to-sequence model [59], variational auto-encoder (VAE) [44], generative adversarial network (GAN) [36], attention mechanism [27, 56], memory-augmented neural network [39, 58], skip neural network [6], temporal difference VAE [40], stochastic neural network [3, 47], stochastic temporal convolutional network [1], predictive state neural network [31], and policy neural network [49, 74]. Enhancing the prior/posterior representation is addressed [53, 62]. We present how these models are connected and why they work for a variety of applications on symbolic and complex patterns in natural language. The variational inference an

关键词： deep learning Bayesian learning data mining information retrieval natural language processing

来源：评论

学校读者我要写书评

暂无评论

MR image Denoising Using Adaptive Wavelet Soft Thresholding

MR Image Denoising Using Adaptive Wavelet Soft Thresholding

引用

International conference on VLSI, Communications, and Signal processing (VCAS)

作者： Sahu, Sima Singh, Harsh Vikram Singh, Amit Kumar Kumar, Basant Dr APJ Abdul Kalam Tech Univ Lucknow Uttar Pradesh India Kamla Nehru Inst Technol KNIT Dept Elect Sultanpur Uttar Pradesh India NIT Dept Comp Sci & Engn Patna Bihar India Motilal Nehru NIT Dept ECE Allahabad Uttar Pradesh India

ISBN: (纸本)9789813297753;9789813297746

Medical imaging has played an important role in medical disease detection, diagnosis, and research related findings and therapy. Removal of noise in a medical image is mandatory step for quality assessment. This paper presents a feature preserved Magnetic Resonance (MR) denoising algorithm which is based on well-accepted multiresolution and statistical modeling. An adaptive wavelet soft thresholding method is designed to remove Gaussian noise from MR image. Orthogonality property of the wavelet transform is used to find the noise variance, using a Median Absolute Deviation (MAD) estimator. Distribution parameters of the wavelet coefficients are estimated by modeling the coefficients using a Normal Inverse Gaussian (NIG) probability density function (PDF). The threshold value is calculated considering the noise and signal information and the wavelet coefficients are updated accordingly. Estimation and analysis of the performance of the proposed method is performed using peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) performance evaluation parameters;these parameters demonstrate the noise suppression ability of the proposed method. Superiority of the proposed denoising method is further established through visual inspection of the denoised images obtained from proposed as well as other contemporary reported methods.

关键词： Multiresolution Denoising Soft thresholding statistical modeling

来源：评论

学校读者我要写书评

暂无评论

Markov Chain Monte Carlo methods for Fluid Flow Forecasting in the Subsurface 20th

Markov Chain Monte Carlo Methods for Fluid Flow Forecasting ...

引用

20th Annual International conference on Computational Science (ICCS)

作者： Ali, Alsadig Al-Mamun, Abdullah Pereira, Felipe Rahunanthan, Arunasalam Univ Texas Dallas Dept Math Sci Richardson TX 75080 USA United Int Univ Inst Nat Sci Dhaka Bangladesh Cent State Univ Dept Math & Comp Sci Wilberforce OH 45384 USA

ISBN: (纸本)9783030504366;9783030504359

Accurate predictions in subsurface flows require the forecasting of quantities of interest by applying models of subsurface fluid flow with very little available data. In general a Bayesian statistical approach along with a Markov Chain Monte Carlo (MCMC) algorithm can be used for quantifying the uncertainties associated with subsurface parameters. However, the complex nature of flow simulators presents considerable challenges to accessing inherent uncertainty in all flow simulator parameters of interest. In this work we focus on the transport of contaminants in a heterogeneous permeability field of a aquifer. In our problem the limited data comes in the form of contaminant fractional flow curves at monitoring wells of the aquifer. We then employ a Karhunen-Loeve expansion to truncate the stochastic dimension of the permeability field and thus the expansion helps reducing the computational burden. Aiming to reduce the computational burden further, we code our numerical simulator using parallel programming procedures on Graphics processing Units (GPUs). In this paper we mainly present a comparative study of two well-known MCMC methods, namely, two-stage and DiffeRential Evolution Adaptive Metropolis (DREAM), for the characterization of the two-dimensional aquifer. A thorough statistical analysis of ensembles of the contaminant fractional flow curves from both MCMC methods is presented. The analysis indicates that although the average fractional flow curves are quite similar, both time-dependent ensemble variances and posterior analysis are considerably distinct for both methods.

关键词： Porous media Contaminant transport Two-stage MCMC DREAM MPSRF

来源：评论

学校读者我要写书评

暂无评论

Novel Convoluted Local Energy Oriented Patten(CLEOP) for the Classification of Wireless Capsule Endoscopy images

Novel Convoluted Local Energy Oriented Patten(CLEOP) for the...

引用

Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON), International conference on

作者： Niranjan. E P. Dayananda JSS Academy of Technical Education Bangalore India BIT Bengaluru India

ISBN: (纸本)9781665400183

Endoscopy enables Physician to identify inflammation, ulcers, and tumors by viewing the intestines and other organs of the digestive systems of a human being. Upper endoscopy examination inside digestive system gives better accuracy when compared to X-rays in detecting abnormal growths caused by cancer and other diseases. Automation in medical image processing has enhanced the prediction of affected layer from the source of image. In that, image analysis in endoscopic medical field was focused on high level prediction and to estimate proper and better treatment for patients at earlier stage with less amount of stress. There are several methods of image analysis to extract the features of the image and predict its category. For better prediction model, the features of that image should be rotational invariant to find the best match training set. To improve the feature extraction in image processing application, texture patterns performed with better efficiency to analyze an image. In this proposed work, a novel method of texture pattern analysis method employed to classify the endoscopic image. This was achieved by using the Convoluted Local Energy Oriented Pattern (CLEOP) based feature extraction method. For validating the performance of proposed work, the CVC-ClinicDB image database was used in the testing process. In that, the database was separated into two major types based on the level of affected tissue region and its size. The efficiency of CLEOP texture pattern extraction method is compared with other state-of-the-art methods of feature extraction and classification model. This can be justified by estimating the statistical parameters estimated by validating the ground-truth of image database.

关键词： Wireless communication image analysis Endoscopes image databases X-rays Feature extraction Cameras

来源：评论

学校读者我要写书评

暂无评论

Algorithm of image de-noising for Gaussian-Gaussian mixed noise model based on stochastic resonance 11

Algorithm of image de-noising for Gaussian-Gaussian mixed no...

引用

11th International conference on Digital image processing (ICDIP)

作者： Chen, Jianxin Zhang, Yu Song, Jiazhong Hangzhou Dianzi Univ Sch Elect & Informat Hangzhou 310018 Peoples R China

ISBN: (数字)9781510630765

ISBN: (纸本)9781510630765

It is of great significance to image de-noising since the image has been the main medium of acquiring and transmitting information in human life. The image is not only destroyed by signal-independent noise, but also destroyed by signal-dependent noise largely. In order to fill the gap between stochastic resonance for image processing with signal-independent noise and signal-dependent noise and eliminate the shortcoming of unsatisfactory processing results of image in the traditional image de-noising methods, an algorithm of image de-noising for Gaussian-Gaussian mixed noise based on stochastic resonance is innovatively proposed in this paper. And three main steps involved are image segmentation, add mixed noise to the image and stochastic resonance processing. First, the original image is clustered and segmented to obtain multiple regions. Then, signal-independent Gaussian noise and signal-dependent Gaussian noise are added to the image in sequence. Finally the multiple noisy regions are respectively processing by stochastic resonance. The proposed method is experimented with different noise variance combinations. The experimental results show that the proposed method can achieve higher peak-signal-to-noise (PSNR) and structural similarity (SSIM), and meanwhile the visual effect is also better.

关键词： signal-independent noise signal-dependent noise Gaussian-Gaussian mixed noise stochastic resonance

来源：评论

学校读者我要写书评

暂无评论

A quantitative validation of segmented colon in virtual colonoscopy using image moments

引用

BIOMEDICAL JOURNAL 2020年第1期43卷 74-82页

作者： Manjunath, K. N. Prabhu, G. K. Siddalingaswamy, P. C. Manipal Acad Higher Educ Manipal Inst Technol Comp Sci & Engn Tiger Circle Rd Manipal 576104 Karnataka India Manipal Univ Elect & Commun Jaipur 303007 Rajasthan India

Background: Evaluation of segmented colon is one of the challenges in Computed Tomography Colonography (CTC). The objective of the study was to measure the segmented colon accurately using image processing techniques. methods: This was a retrospective study, and the Institutional Ethical clearance was obtained for the secondary dataset. The technique was tested on 85 CTC dataset. The CTC dataset of 100-120 kVp, 100 mA, and ST (Slice Thickness) of 1.25 and 2.5 mm were used for empirical testing. The initial results of the work appear in the conference proceedings. Post colon segmentation, three distance measurement techniques, and one volumetric overlap computation were applied in Euclidian space in which the distances were measured on MPR views of the segmented and unsegmented colons and the volumetric overlap calculation between these two volumes. Results: The key finding was that the measurements on both the segmented and the unsegmented volumes remain same without much difference noticed. This was statistically proved. The results were validated quantitatively on 2D MPR images. An accuracy of 95.265+0.4551% was achieved through volumetric overlap computation. Through paired t - test, at alpha = 5%, statistical values were p = 0.6769, and t = 0.4169 which infer that there was no much significant difference. Conclusion: The combination of different validation techniques was applied to check the robustness of colon segmentation method, and good results were achieved with this approach. Through quantitative validation, the results were accepted at alpha = 5%.

关键词： Euclidean space Colon segmentation Quantitative analysis Spatial features Volumetric overlap

来源：评论

学校读者我要写书评

暂无评论

stochastic optimization of areas under precision-recall curves with provable convergence 21

Stochastic optimization of areas under precision-recall curv...

引用

Proceedings of the 35th International conference on Neural Information processing Systems

作者： Qi Qi Youzhi Luo Zhao Xu Shuiwang Ji Tianbao Yang Department of Computer Science The University of Iowa Department of Computer Science & Engineering Texas A&M University

ISBN: (纸本)9781713845393

Areas under ROC (AUROC) and precision-recall curves (AUPRC) are common metrics for evaluating classification performance for imbalanced problems. Compared with AUROC, AUPRC is a more appropriate metric for highly imbalanced datasets. While stochastic optimization of AUROC has been studied extensively, principled stochastic optimization of AUPRC has been rarely explored. In this work, we propose a principled technical method to optimize AUPRC for deep learning. Our approach is based on maximizing the averaged precision (AP), which is an unbiased point estimator of AUPRC. We cast the objective into a sum of coupled compositional functions with inner functions dependent on random variables of the outer level. We propose efficient adaptive and non-adaptive stochastic algorithms named SOAP with provable convergence guarantee under mild conditions by leveraging recent advances in stochastic compositional optimization. Extensive experimental results on image and graph datasets demonstrate that our proposed method outperforms prior methods on imbalanced problems in terms of AUPRC. To the best of our knowledge, our work represents the first attempt to optimize AUPRC with provable convergence. The SOAP has been implemented in the libAUC library

关键词：

来源：评论

学校读者我要写书评

暂无评论

SCW-SGD: stochastically Confidence-Weighted SGD

SCW-SGD: Stochastically Confidence-Weighted SGD

引用

IEEE International conference on image processing

作者： Takumi Kobayashi National Institute of Advanced Industrial Science and Technology 1-1-1 Umezono Tsukuba Ibaraki Japan

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

As the field of deep learning has been rapidly growing, the optimization methods (optimizers) gain keen attention for efficiently training neural networks. While SGD exhibits practically favorable performance on various tasks, adaptive methods, such as ADAM, are also formulated to equip the gradient-based updating with adaptive scaling in a sophisticated way. In this paper, we propose a novel optimizer to integrate those two approaches of the adaptive method and SGD through assigning stochastic confidence weights to the gradient-based updating. We define statistical uncertainty of the gradients which is implicitly embedded in the adaptive scaling of ADAM, and then based on the uncertainty, naturally incorporate stochasticity into the optimizer as a bridge between SGD and ADAM. Thereby, the proposed optimizer, SCWSGD, endows the parameter updating with two types of stochasticity regarding multiplicative scaling for the gradient and mini-batch sampling to compute the gradient, for improving generalization performance. In the experiments on image classification using various CNNs, the proposed optimizer produces favorable performance in comparison to the other optimizers.

关键词： Uncertainty Perturbation methods Training stochastic processes Neural networks Optimization Robustness

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：