【综述】最新7篇数据科学/深度学习/CNN/知识图谱/文本匹配等中英文综述论文推介（附下载）

2017 年 12 月 2 日 专知专知内容组（编）

点击上方“专知”关注获取专业AI知识!

【导读】专知内容组整理了最近人工智能领域相关期刊的7篇最新综述文章，为大家进行介绍，欢迎查看!

▌深度文本匹配综述

作者：庞亮兰艳艳徐君郭嘉丰万圣贤程学旗

摘要：自然语言理解的许多任务,例如信息检索、自动问答、机器翻译、对话系统、复述问题等等,都可以抽象成文本匹配问题.过去研究文本匹配主要集中在人工定义特征之上的关系学习,模型的效果很依赖特征的设计.最近深度学习自动从原始数据学习特征的思想也影响着文本匹配领域,大量基于深度学习的文本匹配方法被提出,作者称这类模型为深度文本匹配模型.相比于传统方法,深度文本匹配模型能够从大量的样本中自动提取出词语之间的关系,并能结合短语匹配中的结构信息和文本匹配的层次化特性,更精细地描述文本匹配问题.根据特征提取的不同结构,深度文本匹配模型可以分为3类:基于单语义文档表达的深度学习模型、基于多语义文档表达的深度学习模型和直接建模匹配模式的深度学习模型.从文本交互的角度,这3类模型具有递进的关系,并且对于不同的应用,具有各自性能上的优缺点.该文在复述问题、自动问答和信息检索3个任务上的经典数据集上对深度文本匹配模型进行了实验,比较并详细分析了各类模型的优缺点.最后该文对深度文本模型未来发展的若干问题进行了讨论和分析。

期刊：计算机学报 2017年4月第4期

网址：

http://cjc.ict.ac.cn/online/onlinepaper/pl-201745181647.pdf

▌Deep Convolutional Neural Networks for Image Classification - A Comprehensive Review

作者：Waseem Rawat Zenghui Wang

摘要：Convolutional neural networks (CNNs) have been applied to visual tasks since the late 1980s. However, despite a few scattered applications, they were dormant until the mid-2000s when developments in computing power and the advent of large amounts of labeled data, supplemented by improved algorithms, contributed to their advancement and brought them to the forefront of a neural network renaissance that has seen rapid progression since 2012. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art deep learning systems. Along the way, we analyze (1) their early successes, (2) their role in the deep learning renaissance, (3) selected symbolic works that have contributed to their recent popularity, and (4) several improvement attempts by reviewing contributions and challenges of over 300 publications. We also introduce some of their current trends and remaining challenges.

期刊：Neural Computation 2017年09月

网址：

http://ieeexplore.ieee.org/document/8016501/

▌Data Science: A Comprehensive Overview

作者：Longbing Cao

摘要：The 21st century has ushered in the age of big data and data economy, in which data DNA, which carries important knowledge, insights, and potential, has become an intrinsic constituent of all data-based organisms. An appropriate understanding of data DNA and its organisms relies on the new field of data science and its keystone, analytics. Although it is widely debated whether big data is only hype and buzz, and data science is still in a very early phase, significant challenges and opportunities are emerging or have been inspired by the research, innovation, business, profession, and education of data science. This article provides a comprehensive survey and tutorial of the fundamental aspects of data science: the evolution from data analysis to data science, the data science concepts, a big picture of the era of data science, the major challenges and directions in data innovation, the nature of data analytics, new industrialization and service opportunities in the data economy, the profession and competency of data education, and the future of data science. This article is the first in the field to draw a comprehensive big picture, in addition to offering rich observations, lessons, and thinking about data science and analytics.

期刊：ACM Computing Surveys (CSUR) 2017年10月

网址：https://dl.acm.org/citation.cfm?

id=3076253&CFID=1012531090&CFTOKEN=28945038

▌Knowledge Graph Embedding: A Survey of Approaches and Applications

作者：Waseem Rawat Zenghui Wang

摘要：Knowledge graph (KG) embedding is to embed components of a KG including entities and relations into continuous vector spaces, so as to simplify the manipulation while preserving the inherent structure of the KG. It can benefit a variety of downstream tasks such as KG completion and relation extraction, and hence has quickly gained massive attention. In this article, we provide a systematic review of existing techniques, including not only the state-of-the-arts but also those with latest trends. Particularly, we make the review based on the type of information used in the embedding task. Techniques that conduct embedding using only facts observed in the KG are first introduced. We describe the overall framework, specific model design, typical training procedures, as well as pros and cons of such techniques. After that, we discuss techniques that further incorporate additional information besides facts. We focus specifically on the use of entity types, relation paths, textual descriptions, and logical rules. Finally, we briefly introduce how KG embedding can be applied to and benefit a wide variety of downstream tasks such as KG completion, relation extraction, question answering, and so forth.

期刊：IEEE Transactions on Knowledge and Data Engineering ( Volume: 29, Issue: 12, Dec. 1 2017 )

网址：

http://ieeexplore.ieee.org/document/8047276/

▌深度学习认知计算综述

作者：陈伟宏安吉尧李仁发李万里

摘要：随着大数据和智能时代的到来，机器学习的研究重心已开始从感知领域转移到认知计算（Cognitive computing，CC）领域，如何提升对大规模数据的认知能力已成为智能科学与技术的一大研究热点，最近的深度学习有望开启大数据认知计算领域的研究新热潮.本文总结了近年来大数据环境下基于深度学习的认知计算研究进展，分别从深度学习数据表示、认知模型、深度学习并行计算及其应用等方面进行了前沿概况、比较和分析，对面向大数据的深度学习认知计算的挑战和发展趋势进行了总结、思考与展望。

期刊：自动化学报 2017年11月第11期

网址：

http://www.aas.net.cn/CN/abstract/abstract19164.shtml

▌统计机器学习中参数可辨识性研究及其关键问题

作者：冉智勇, 胡包钢

摘要：参数可辨识性研究在统计机器学习中具有重要的理论意义和应用价值.参数可辨识性是关于模型参数能否被惟一确定的性质.在包含物理参数的学习模型中，可辨识性不仅是物理参数获得正确估计的前提条件，更重要的是，它反映了学习机器中由参数决定的物理特征.为扩展到未来类人智能机器研究的考察视角，我们将学习模型纳入"知识与数据共同驱动模型"的框架中讨论.在此框架下，我们提出两个关键问题.第一是参数可辨识性准则问题.该问题考察与可辨识性密切相关的各种判断准则，其中知识驱动子模型与数据驱动子模型的耦合方式为参数可辨识性问题提供了新的研究空间.第二是参数可辨识性与机器学习理论和应用相关联的研究.该研究包括可辨识性对参数估计、模型选择、学习算法、学习动态过程、奇异学习理论、贝叶斯推断等内容的深刻影响。

期刊：自动化学报 2017年10月第10期

网址：

http://www.aas.net.cn/CN/abstract/abstract19146.shtml

▌深度文本匹配综述

作者：庞亮兰艳艳徐君郭嘉丰万圣贤程学旗

期刊：计算机学报 2017年4月第4期

网址：

http://cjc.ict.ac.cn/online/onlinepaper/pl-201745181647.pdf

▌卷积神经网络研究综述

作者：周飞燕金林鹏董军

摘要：本文首先概述了卷积神经网络的发展历史,然后分别描述了神经元模型、多层感知器的结构。接着,详细分析了卷积神经网络的结构,包括卷积层、取样层、全连接层,它们发挥着不同的作用。然后,讨论了网中网结构、空间变换网络等改进的卷积神经网络。同时,还分别介绍了卷积神经网络的监督学习、无监督学习训练方法以及一些常用的开源工具。此外,本文以图像分类、人脸识别、音频检索、心电图分类及目标检测等为例,对卷积神经网络的应用作了归纳。卷积神经网络与递归神经网络的集成是一个途径。为了给读者以尽可能多的借鉴,本文还设计并试验了不同参数及不同深度的卷积神经网络以图把握各参数间的相互关系及不同参数设置对结果的影响。最后,给出了卷积神经网络及其应用中待解决的若干问题。

期刊：计算机学报 2017年6月

网址：

http://cjc.ict.ac.cn/online/cre/zfy-2017611182348-2017811154835.pdf

特别提示-相关综述论文下载：

请关注专知公众号（扫一扫最下面专知二维码，或者点击上方蓝色专知），