检索结果-内蒙古大学图书馆

Learning data-adaptive nonparametric kernels

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Huang, Xiaolin Gong, Chen Yang, Jie Li, Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Automation Tsinghua University

Kernel methods have been extensively used in a variety of machine learning tasks such as classification, clustering, and dimensionality reduction. For complicated practical tasks, the traditional kernels, e.g., Gaussian kernel and sigmoid kernel, or their combinations are often not sufficiently flexible to fit the data. In this paper, we present a Data-Adaptive Nonparametric Kernel (DANK) learning framework in a data-driven manner. To be specific, in model formulation, we impose an adaptive matrix on the kernel/Gram matrix in an entry-wise strategy. Since we do not specify the formulation of the adaptive matrix, each entry in the adaptive matrix can be directly and flexibly learned from the data. Therefore, the solution space of the learned kernel is largely expanded, which makes our DANK model flexible to capture the data with different local statistical properties. Specifically, the proposed kernel learning framework can be seamlessly embedded to support vector machines (SVM) and support vector regression (SVR), which has the capability of enlarging the margin between classes and reducing the model generalization error. Theoretically, we demonstrate that the objective function of our DANK model embedded in SVM/SVR is gradient-Lipschitz continuous. Thereby, the training process for kernel and parameter learning in SVM/SVR can be efficiently optimized in a unified framework. Further, to address the scalability issue in nonparametric kernel learning framework, we decompose the entire optimization problem in DANK into several smaller easy-to-solve problems, so that our DANK model can be efficiently approximated by this partition. The effectiveness of this approximation is demonstrated by both empirical studies and theoretical guarantees. Experimentally, the proposed DANK model embedded in SVM/SVR achieves encouraging performance on various classification and regression benchmark datasets when compared with other representative kernel learning based algorithms. Copyrig

关键词： Matrix algebra

Correction to: Automatic identification of myopic maculopathy related imaging features in optic disc region via machine learning methods

学校读者我要写书评

暂无评论

Journal of translational medicine 2021年第1期19卷 203页

作者： Yuchen Du Qiuying Chen Ying Fan Jianfeng Zhu Jiangnan He Haidong Zou Dazhen Sun Bowen Xin David Feng Michael Fulham Xiuying Wang Lisheng Wang Xun Xu Department of Automation The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University (SJTU) 800 Dongchuan RD. Minhang District Shanghai 200240 People's Republic of China. Department of Preventative Ophthalmology Shanghai Eye Diseases Prevention and Treatment Center Shanghai Eye Hospital No. 380 Kangding Road Shanghai 200040 China. Department of Ophthalmology Shanghai Key Laboratory of Ocular Fundus Diseases Shanghai Engineering Center for Visual Science and Photo Medicine Shanghai General Hospital SJTU School of Medicine Shanghai China. National Clinical Research Center for Eye Diseases Shanghai 20080 China. Biomedical and Multimedia Information Technology Research Group School of Computer Science The University of Sydney Sydney NSW 2006 Australia. Department of Molecular Imaging Royal Prince Alfred Hospital and the University of Sydney Sydney Australia. Department of Automation The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University (SJTU) 800 Dongchuan RD. Minhang District Shanghai 200240 People's Republic of China. lswang@***. Department of Preventative Ophthalmology Shanghai Eye Diseases Prevention and Treatment Center Shanghai Eye Hospital No. 380 Kangding Road Shanghai 200040 China. drxuxun@***. Department of Ophthalmology Shanghai Key Laboratory of Ocular Fundus Diseases Shanghai Engineering Center for Visual Science and Photo Medicine Shanghai General Hospital SJTU School of Medicine Shanghai China. drxuxun@***. National Clinical Research Center for Eye Diseases Shanghai 20080 China. drxuxun@***.

An amendment to this paper has been published and can be accessed via the original article.

关键词：

<i>L</i>(2,1)-Labeling of the Brick Product Graphs

学校读者我要写书评

暂无评论

Journal of Applied Mathematics and Physics 2017年第8期5卷 1529-1536页

作者： Xiujun Zhang Hong Yang Hong Li School of Information Science and Engineering Chengdu University Chengdu China Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu University Chengdu China

A k-L(2,1)-labeling for a graph G is a function such that whenever and whenever u and v are at distance two apart. The λ-number for G, denoted by λ(G), is the minimum k over all k-L(2,1)-labelings of G. In this paper, we show that for or 11, which confirms Conjecture 6.1 stated in [X. Li, V. Mak-Hau, S. Zhou, The L(2,1)-labelling problem for cubic Cayley graphs on dihedral groups, J. Comb. Optim. (2013) 25: 716-736] in the case when or 11. Moreover, we show that? if 1) either (mod 6), m is odd, r = 3, or 2) (mod 3), m is even (mod 2), r = 0.

关键词： Graph Labeling Brick Product Graph L((2 1)-Labeling Frequency Assignment Problem

Generalization Properties of hyper-RKHS and its Applications

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Shi, Lei Huang, Xiaolin Yang, Jie Suykens, Johan A.K. Department of Electrical Engineering ESAT-STADIUS KU Leuven Kasteelpark Arenberg 10 LeuvenB-3001 Belgium Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai200433 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view. Algorithmically, we consider two regularized regression models with bivariate forms in this space, including kernel ridge regression (KRR) and support vector regression (SVR) endowed with hyper-RKHS, and further combine divide-and-conquer with Nyström approximation for scalability in large sample cases. This framework is general: the underlying kernel is learned from a broad class, and can be positive definite or not, which adapts to various requirements in kernel learning. Theoretically, we study the convergence behavior of regularized regression algorithms in hyper-RKHS and derive the learning rates, which goes beyond the classical analysis on RKHS due to the non-trivial independence of pairwise samples and the characterisation of hyper-RKHS. Experimentally, results on several benchmarks suggest that the employed framework is able to learn a general kernel function form an arbitrary similarity matrix, and thus achieves a satisfactory performance on classification tasks. Copyright © 2018, The Authors. All rights reserved.

关键词： Approximation theory

DNA Sequence Alignment Algorithm Based on k-tuple Statistics

学校读者我要写书评

暂无评论

DNA Sequence Alignment Algorithm Based on k-tuple Statistics

2017 2nd International Conference on Software, Multimedia and Communication Engineering（SMCE 2017)

作者： Jun-yan ZHANG Chen-hui YANG Hai-ying WANG College of Information Science and Engineering Chengdu UniversityChengdu 610106China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University

DNA Sequence Alignment is one of the most basic and most important operations in *** this paper,we put forward to SDk S algorithm based on k-tuple statistic,which is a kind of probability *** positive transition probability matrix,the negative transition probability matrix,and the logarithmic ration are computed based on Markov *** obtaining converting sequence,we get the results of k-tuple ***,the similarity measurement can be gained according to above *** the minimum support is given,we can identify two DNA sequences is similarity or *** experimental results show that SDk S algorithm has better effective performance in saving computing time.

关键词： Sequence alignment k-tuple statistic Markov model Similarity measurement

3D RoI-aware U-net for accurate and efficient colorectal tumor segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Huang, Yi-Jie Dou, Qi Wang, Zi-Xian Liu, Li-Zhi Jin, Ying Li, Chao-Feng Wang, Lisheng Chen, Hao Xu, Rui-Hua Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University China Imsight Medical Technology Co. Ltd. China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Sun Yat-sen University Cancer Center State Key Laboratory of Oncology in South China Collaborative Innovation Center for Cancer Medicine Guangzhou China

Segmentation of colorectal cancerous regions from 3D Magnetic Resonance (MR) images is a crucial procedure for radiotherapy which conventionally requires accurate delineation of tumour boundaries at an expense of labor, time and reproducibility. While deep learning based methods serve good baselines in 3D image segmentation tasks, small applicable patch size limits effective receptive field and degrades segmentation performance. In addition, Regions of interest (RoIs) localization from large whole volume 3D images serves as a preceding operation that brings about multiple benefits in terms of speed, target completeness, reduction of false positives. Distinct from sliding window or non-joint localization-segmentation based models, we propose a novel multitask framework referred to as 3D RoI-aware U-Net (3D RU-Net), for RoI localization and in-region segmentation where the two tasks share one backbone encoder network. With the region proposals from the encoder, we crop multi-level RoI in-region features from the encoder to form a GPU memory-efficient decoder for detail-preserving segmentation and therefore enlarged applicable volume size and effective receptive field. To effectively train the model, we designed a Dice formulated loss function for the global-to-local multi-task learning procedure. Based on the efficiency gains demonstrated by the proposed method, we went on to ensemble models with different receptive fields to achieve even higher performance costing minor extra computational expensiveness. Extensive experiments were subsequently conducted on 64 cancerous cases with a four-fold cross-validation, and the results showed significant superiority in terms of accuracy and efficiency over conventional state-of-the art frameworks. In conclusion, the proposed method has a huge potential for extension to other 3D object segmentation tasks from medical images due to its inherent generalizability. The code for the proposed method is publicly available. Copyright ©

关键词： Signal encoding

Cross-media analysis and reasoning: advances and directions

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2017年第1期18卷 44-57页

作者： Yu-xin PENG Wen-wu ZHU Yao ZHAO Chang-sheng XU Qing-ming HUANG Han-qing LU Qing-hua ZHENG Tie-jun HUANG Wen GAO Institute of Computer Science and Technology Peking University Department of Computer Science and Technology Tsinghua University Institute of Information Science Beijing Jiaotong University National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Sciences Department of Computer Science and Technology Xi'an Jiaotong University School of Electronics Engineering and Computer Science Peking University

Cross-media analysis and reasoning is an active research area in computer science, and a promising direction for artificial intelligence. However, to the best of our knowledge, no existing work has summarized the state-of-the-art methods for cross-media analysis and reasoning or presented advances, challenges, and future directions for the field. To address these issues, we provide an overview as follows：（1） theory and model for cross-media uniform representation; （2） cross-media correlation understanding and deep mining; （3） cross-media knowledge graph construction and learning methodologies; （4） cross-media knowledge evolution and reasoning; （5） cross-media description and generation; （6） cross-media intelligent engines; and （7） cross-media intelligent applications. By presenting approaches, advances, and future directions in cross-media analysis and reasoning, our goal is not only to draw more attention to the state-of-the-art advances in the field, but also to provide technical insights by discussing the challenges and research directions in these areas.

关键词： Cross-media analysis Cross-media reasoning Cross-media applications

Fast KNN search for big data with set compression tree and best bin first 2

学校读者我要写书评

暂无评论

Fast KNN search for big data with set compression tree and b...

2nd International Conference on Cloud Computing and Internet of Things, CCIOT 2016

作者： Chen, Zhenjie Yan, Jingqi Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of Ministry of Education for System Control and Information Processing China Shanghai China

ISBN: (纸本)9781467398213

This paper proposes k nearest neighbors (kNN) search based on set compression tree (SCT) and best bin first (BBF) to deal with the problem for big data. The large compression rate by set compression tree is achieved by compressing the set of descriptors jointly instead of compressing on a per-descript or basis. So set compression tree has a good performance in kNN search at a low bit rate. At the same time, the best bin first (BBF) is a very efficient algorithm to find the approximately kNN from a large number of high dimensional feature descriptors. SCT-BBF is a novel exploration and it improves search performance in three aspects: First, SCT-BBF requires less memory footprint, which is important in big data age. Second, it increases accuracy compared traditional method like KD-Tree and original SCT. SCT-BBF can be used with other data processing methods like PCA and SIFT to perform better. Third, this paper adopts finer search to increase accuracy at a slight loss of speed. And it can extend to big data easily. © 2016 IEEE.

关键词： Big data

Nonconvex penalties with analytical solutions for one-bit compressive sensing

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Huang, Xiaolin Yan, Ming Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing Shanghai200240 China Department of Computational Mathematics Science and Engineering Department of Mathematics Michigan State University East LansingMI48824 United States

One-bit measurements widely exist in the real world and can be used to recover sparse signals. This task is known as one-bit compressive sensing (1bit-CS). In this paper, we propose novel algorithms based on both convex and nonconvex sparsity-inducing penalties for robust 1bit-CS. We consider the dual problem, which has only one variable and provides a sufficient condition to verify whether a solution is globally optimal or not. For positive homogeneous penalties, a globally optimal solution can be obtained in two steps: a proximal operator and a normalization step. For other penalties, we solve the dual problem, and it needs to evaluate the proximal operators for many times. Then we provide fast algorithms for finding analytical solutions for three penalties: minimax concave penalty (MCP), 0norm, and sorted 1penalty. Specifically, our algorithm is more than 200 times faster than the existing algorithm for MCP. Its efficiency is comparable to the algorithm for the 1penalty in time, while its performance is much better than 1. Among these penalties, sorted 1is most robust to noise in different settings. Copyright © 2017, The Authors. All rights reserved.

关键词： Compressed sensing