混合-增强智能:协作与认知（英文）

被引：68

作者：

Nanning ZHENG ^{[1
,2
]}

Ziyi LIU ^{[1
,2
]}

Pengju REN ^{[1
,2
]}

Yongqiang MA ^{[1
,2
]}

Shitao CHEN ^{[1
,2
]}

Siyu YU ^{[1
,2
]}

Jianru XUE ^{[1
,2
]}

Badong CHEN ^{[1
,2
]}

Feiyue WANG ^{[3
]}

机构：

[1] Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University

[2] National Engineering Laboratory of Visual Information Processing Applications,Xi'an Jiaotong University

[3] State Key Laboratory of Management and Control for Complex Systems, Institute of Automation,Chinese Academy of Sciences

来源：

FrontiersofInformationTechnology&ElectronicEngineering | 2017年 / 18卷 / 02期

关键词：

人-机协同; 混合增强智能; 认知计算; 直觉推理; 因果模型; 认知映射; 视觉场景理解; 自主驾驶汽车;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

人工智能追求的长期目标是使机器能像人一样学习和思考。由于人类面临的许多问题具有不确定性、脆弱性和开放性,任何智能程度的机器都无法完全取代人类,这就需要将人的作用或人的认知模型引入到人工智能系统中,形成混合-增强智能的形态,这种形态是人工智能或机器智能的可行的、重要的成长模式。混合-增强智能可以分为两类基本形式:一类是人在回路的人机协同混合增强智能,另一类是将认知模型嵌入机器学习系统中,形成基于认知计算的混合智能。本文讨论人机协同的混合-增强智能的基本框架,以及基于认知计算的混合-增强智能的基本要素:直觉推理与因果模型、记忆和知识演化;特别论述了直觉推理在复杂问题求解中的作用和基本原理,以及基于记忆与推理的视觉场景理解的认知学习网络;阐述了竞争-对抗式认知学习方法,并讨论了其在自动驾驶方面的应用;最后给出混合-增强智能在相关领域的典型应用。

引用

页码：153 / 180

页数：28

共 35 条

[21]

Assessing the Vulnerability of Social-Environmental Systems[J] . Hallie Eakin,Amy Lynd Luers.Annual Review of Environment and Resources . 2006 (0)

[22]

The perception of causality in infancy[J] . Rebecca Saxe,Susan Carey.Acta Psychologica . 2006 (1)

[23]

Perceived physical and social causality in animated motions: Spontaneous reports and ratings[J] . Anne Schlottmann,Elizabeth D. Ray,Anne Mitchell,Nathalie Demetriou.Acta Psychologica . 2006 (1)

[24]

Whose gaze will infants follow? The elicitation of gaze‐following in 12‐month‐olds[J] . SusanJohnson,VirginiaSlaughter,SusanCarey.Developmental Science . 2002 (2)

[25]

Deep Blue[J] . Murray Campbell,A.Joseph Hoane,Feng-hsiung Hsu.Artificial Intelligence . 2001 (1)

[26]

The Qualification Problem: A solution to the problem of anomalous models[J] . Michael Thielscher.Artificial Intelligence . 2001 (1)

[27] On agent-based software engineering [J].

Jennings, NR .

ARTIFICIAL INTELLIGENCE, 2000, 117 (02) :277-296

[28] Activation in human MT/MST by static images with implied motion [J].

Kourtzi, Z ;

Kanwisher, N .

JOURNAL OF COGNITIVE NEUROSCIENCE, 2000, 12 (01) :48-55

[29] A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots [J].

Sebastian Thrun ;

Wolfram Burgard ;

Dieter Fox .

Autonomous Robots, 1998, 5 :253-271

[30]

Infants Attribute Value＆plusmn;to the Goal-Directed Actions of Self-propelled Objects[J] . David Premack,Ann James Premack.Journal of Cognitive Neuroscience . 1997 (6)

← 1 2 3 4 →