Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
基本信息
- 批准号:RGPIN-2018-06768
- 负责人:
- 金额:$ 2.84万
- 依托单位:
- 依托单位国家:加拿大
- 项目类别:Discovery Grants Program - Individual
- 财政年份:2018
- 资助国家:加拿大
- 起止时间:2018-01-01 至 2019-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
With the ever-growing number of mobile devices, as well as the widespread deployment of surveillance systems and sensor networks, an unprecedented amount of data is being generated and collected. Data compression techniques are playing an increasingly important role in meeting the significant challenges in storing, transmitting, processing, and analyzing such data. The proposed research aims to develop a theory of learning-oriented data compression, investigate the relevant algorithm design, and explore the practical applications of this new data compression paradigm. It represents a stepping stone in the long-term goal of developing a full-fledged compression-aware learning theory.******The proposed research consists of three thrusts: centralized compression, distributed compression, and generalized distributed compression.******In a learning-oriented centralized compression system, a source is encoded into a bit string, and based on that string, the decoder produces a probabilistic description of the relevant features of the target data satisfying the prescribed constraints. A unified approach will be developed based on a novel optimization technique for estimating the fundamental compression limits and generating the optimal feature representations. Compact descriptors for video analysis will be constructed based on this approach. This line of work also has the potential of shedding light on the design and compression of deep neural networks. ******Learning-oriented distributed compression generalizes its centralized counterpart by separately encoding disjoint source components. For this problem, traditional approaches based on information geometry are only effective in the low-rate limit. Significant analytical difficulties arise in the high-rate region due to the non-convex nature of the problem. Advanced analytical techniques will be introduced to tackle these difficulties. Among many other applications, the resulting theory will be used to guide the joint design of the signaling and quantizing subsystems in cloud radio access networks.******Learning-oriented generalized distributed data compression is a further extension of distributed data compression that allows arbitrary connections between the source components and the encoders. The theory of learning-oriented generalized distributed data compression, once completed, can be leveraged to design an enhanced predictive coding architecture that is able to achieve the performance limit of noncausal lossy compression.******The proposed research will greatly enrich the theory of data compression and broaden the scope of its applications. The students involved in this research program will receive a balanced and comprehensive training in theory building, algorithm design, and system implementation. The breadth of the insight that they will acquire will enable them to become leaders of this emerging research field.
随着移动设备数量的不断增加,以及监控系统和传感器网络的广泛部署,正在产生和收集前所未有的大量数据。数据压缩技术在应对存储、传输、处理和分析此类数据的重大挑战方面发挥着越来越重要的作用。本研究旨在发展一种面向学习的数据压缩理论,研究相关的算法设计,并探索这种新的数据压缩范式的实际应用。它代表了开发一个成熟的压缩感知学习理论的长期目标的踏脚石。******提出的研究包括三个方向:集中压缩、分布式压缩和广义分布式压缩。******在面向学习的集中式压缩系统中,源被编码成位串,解码器根据该位串生成满足规定约束的目标数据的相关特征的概率描述。基于一种新的优化技术,将开发一种统一的方法来估计基本压缩极限并生成最优特征表示。基于这种方法,将构建用于视频分析的紧凑描述符。这项工作也有可能为深度神经网络的设计和压缩提供启示。******面向学习的分布式压缩通过对不相交的源组件进行单独编码来推广其集中式压缩。对于这一问题,基于信息几何的传统方法仅在低速率极限下有效。由于问题的非凸性,在高速率区域出现了显著的分析困难。将引入先进的分析技术来解决这些困难。在许多其他应用中,所得理论将用于指导云无线接入网络中信令和量化子系统的联合设计。******面向学习的广义分布式数据压缩是分布式数据压缩的进一步扩展,它允许源组件和编码器之间的任意连接。面向学习的广义分布式数据压缩理论一旦完成,就可以用来设计一种增强的预测编码体系结构,该体系结构能够达到非因果有损压缩的性能极限。******所提出的研究将极大地丰富数据压缩理论,拓宽其应用范围。参与本研究计划的学生将在理论建构、演算法设计及系统实作等方面,接受均衡且全面的训练。他们将获得的洞察力的广度将使他们成为这个新兴研究领域的领导者。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Chen, Jun其他文献
Homodiphenylprolinol Methyl Ether as a Highly Efficient Catalyst for Asymmetric Michael Addition of Ketones to Nitroalkenes
高二苯基脯氨醇甲醚作为酮与硝基烯烃不对称迈克尔加成的高效催化剂
- DOI:
- 发表时间:
- 期刊:
- 影响因子:2
- 作者:
Wang, Shi-Wen;Chen, Gui-Hua;Peng, Yun-Gui;Chen, Jun - 通讯作者:
Chen, Jun
Sarcoidosis misdiagnosed as malignant tumors: a case report
- DOI:
10.1186/s12957-015-0748-6 - 发表时间:
2015-12-12 - 期刊:
- 影响因子:3.2
- 作者:
Li, Zuosheng;Li, Xin;Chen, Jun - 通讯作者:
Chen, Jun
Mogroside V Inhibits Hyperglycemia-induced Lung Cancer Cells Metastasis through Reversing EMT and Damaging Cytoskeleton
- DOI:
10.2174/1568009619666190619154240 - 发表时间:
2019-01-01 - 期刊:
- 影响因子:3
- 作者:
Chen, Jun;Jiao, Demin;Chen, Qingyong - 通讯作者:
Chen, Qingyong
Comparison of the relationship between bone marrow adipose tissue and volumetric bone mineral density in children and adults.
- DOI:
10.1016/j.jocd.2013.02.009 - 发表时间:
2014-01 - 期刊:
- 影响因子:2.5
- 作者:
Shen, Wei;Velasquez, Gilbert;Chen, Jun;Jin, Ye;Heymsfield, Steven B.;Gallagher, Dympna;Pi-Sunyer, F. Xavier - 通讯作者:
Pi-Sunyer, F. Xavier
Clinical Characteristics and Prognosis of Penicilliosis among Human Immunodeficiency Virus-Infected Patients in Eastern China
- DOI:
10.4269/ajtmh.16-0521 - 发表时间:
2017-01-01 - 期刊:
- 影响因子:3.3
- 作者:
Chen, Jun;Zhang, Renfang;Lu, Hongzhou - 通讯作者:
Lu, Hongzhou
Chen, Jun的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Chen, Jun', 18)}}的其他基金
Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
- 批准号:
RGPIN-2018-06768 - 财政年份:2022
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
- 批准号:
RGPIN-2018-06768 - 财政年份:2021
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
- 批准号:
RGPIN-2018-06768 - 财政年份:2020
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
LED Controller and Software for Real Time Seamless Video Walls
用于实时无缝视频墙的 LED 控制器和软件
- 批准号:
543225-2019 - 财政年份:2019
- 资助金额:
$ 2.84万 - 项目类别:
Engage Grants Program
Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
- 批准号:
RGPIN-2018-06768 - 财政年份:2019
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Automated Deep Alpha Matting for Vehicle Images
车辆图像的自动深度 Alpha 抠图
- 批准号:
523064-2018 - 财政年份:2018
- 资助金额:
$ 2.84万 - 项目类别:
Engage Grants Program
Toward a Fundamental Theory of Gaussian Source-Channel Networks
走向高斯源通道网络的基本理论
- 批准号:
355601-2013 - 财政年份:2017
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Toward a Fundamental Theory of Gaussian Source-Channel Networks
走向高斯源通道网络的基本理论
- 批准号:
355601-2013 - 财政年份:2016
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Toward a Fundamental Theory of Gaussian Source-Channel Networks
走向高斯源通道网络的基本理论
- 批准号:
355601-2013 - 财政年份:2015
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
A rate-constrained video descriptor based on the information bottleneck principle
基于信息瓶颈原理的速率约束视频描述符
- 批准号:
486615-2015 - 财政年份:2015
- 资助金额:
$ 2.84万 - 项目类别:
Engage Grants Program
相似国自然基金
炭包覆纳米晶的"Oriented Attachment"生长及其多维结构构筑
- 批准号:51572015
- 批准年份:2015
- 资助金额:64.0 万元
- 项目类别:面上项目
相似海外基金
Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
- 批准号:
RGPIN-2018-06768 - 财政年份:2022
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
- 批准号:
RGPIN-2018-06768 - 财政年份:2021
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Improving Machine Learning Methods for Small Human Oriented Data Sets
改进面向小型人类数据集的机器学习方法
- 批准号:
534856-2019 - 财政年份:2021
- 资助金额:
$ 2.84万 - 项目类别:
Postgraduate Scholarships - Doctoral
CAREER: Learning to Sense: Joint Learning of Task Oriented Cognitive Sensing with Data Driven Reconstruction and Inference
职业:学习感知:面向任务的认知感知与数据驱动的重建和推理的联合学习
- 批准号:
2047771 - 财政年份:2021
- 资助金额:
$ 2.84万 - 项目类别:
Continuing Grant
Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
- 批准号:
RGPIN-2018-06768 - 财政年份:2020
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Improving Machine Learning Methods for Small Human Oriented Data Sets
改进面向小型人类数据集的机器学习方法
- 批准号:
534856-2019 - 财政年份:2020
- 资助金额:
$ 2.84万 - 项目类别:
Postgraduate Scholarships - Doctoral
Learning-Oriented Data Compression with Applications
面向学习的数据压缩及其应用
- 批准号:
RGPIN-2018-06768 - 财政年份:2019
- 资助金额:
$ 2.84万 - 项目类别:
Discovery Grants Program - Individual
Improving Machine Learning Methods for Small Human Oriented Data Sets
改进面向小型人类数据集的机器学习方法
- 批准号:
534856-2019 - 财政年份:2019
- 资助金额:
$ 2.84万 - 项目类别:
Postgraduate Scholarships - Doctoral
SaTC: EDU: Captivology-Stimuli-based Learning (CAPITAL) of Big Data Security (BigSec): Towards a Science/Engineering, Career-Oriented Training
SaTC:EDU:大数据安全 (BigSec) 的基于 Captivology-Stimuli 的学习 (CAPITAL):迈向科学/工程、职业导向的培训
- 批准号:
1723250 - 财政年份:2017
- 资助金额:
$ 2.84万 - 项目类别:
Standard Grant
Collaborative Research: Statistical Learning and Object Oriented Data Analysis
协作研究:统计学习和面向对象的数据分析
- 批准号:
0606580 - 财政年份:2006
- 资助金额:
$ 2.84万 - 项目类别:
Standard Grant