2019 年人工智能新态势与新进展

doi:10.11871/jfdc.issn.2096-742X.2019.02.001

数据与计算发展前沿 ›› 2019, Vol. 1 ›› Issue (2): 1-16.

doi: 10.11871/jfdc.issn.2096-742X.2019.02.001

所属专题： “人工智能”专刊

• 人工智能专刊 • 下一篇

2019 年人工智能新态势与新进展

孙哲南^1,^2,^3,^*(),张兆翔^1,^2,³,王威¹,刘菲¹,谭铁牛^1,^2,³

1. 中国科学院自动化研究所,智能感知与计算研究中心,北京 100190
2. 中国科学院大学,人工智能学院,北京 100049
3. 中国科学院脑科学与智能技术卓越创新中心,北京 100190

收稿日期:2019-09-16 出版日期:2019-12-20 发布日期:2020-01-15
通讯作者: 孙哲南
作者简介:孙哲南,1976年生,中国科学院自动化研究所,副总工程师,研究员,博士生导师,中国科学院大学人工智能学院岗位教授,天津中科智能识别产业技术研究院院长,国际模式识别学会会士IAPR Fellow和生物特征识别技术委员会主席,担任国际期刊IEEE Transactions on Biometrics, Behavior, and Identity Science编委。主要研究方向为生物特征识别、模式识别、计算机视觉,发表国际期刊和会议论文200多篇,SCI他引2000多次,H-index指数43,获得国家技术发明二等奖和中国专利优秀奖。本文负责第一章内容。
Sun Zhenan was born in 1976. He is currently a professor in the Institute of Automation, Chinese Academy of Sciences (CASIA). He received the PhD degree in pattern recognition and intelligent systems from CASIA in 2006. His research interests include biometrics, pattern recognition, and computer vision. He has published more than 200 papers with more than 2000 citations from SCI papers. He serves as an Associate Editor of the IEEE Transactions on Biometrics, Behavior, and Identity Science. He is a fellow of the IAPR. He is the corresponding author of the paper and his contribution is writing Section 1.|张兆翔,1983年生,中国科学院自动化研究所模式识别国家重点实验室,研究员,博士生导师,中国科学院脑科学与智能技术卓越创新中心年轻骨干,中国科学院大学岗位教授,IEEE高级会员,中国计算机学会杰出会员、中国人工智能学会杰出会员,入选“国家第四批万人计划青年拔尖人才”。张兆翔博士致力于生物认知启发的视觉感知与理解的理论与方法研究,在可用信息建模和基于模型的物体识别问题上开展了系统工作,在面向国家公共安全和智慧城市监管需求的系统平台上取得成功应用,取得显著社会影响和经济效益,近五年来在国际主流学术期刊与会议上发表论文100余篇,SCI收录期刊论文40余篇,担任了AAAI、IJCAI、NIPS、ICPR等多个国际会议的Area Chair、Senior PC或者PC,SCI期刊《Pattern Recognition》编委、《Neurocomputing》编委、《IEEE Access》编委。在本文中承担基于类脑智能的计算机视觉部分。
Zhang Zhaoxiang received his BSc degree in Department of Electronic Science and Technology from University of Science and Technology of China, and the PhD degree in Pattern Recognition and Intelligent Systems from the Institute of Automation, Chinese Academy of Sciences in 2004 and 2009, respectively. From 2009 to 2015, he worked as a Lecturer, Associate Professor, and later the deputy director of Department of Computer Application Technology at the Beihang University. Since July 2015, Dr. Zhang has joined the National Laboratory of Pattern Recognition (NLPR) where he is currently a Professor. His major research interests include pattern recognition, computer vision, machine learning and bio-inspired visual computing. He has published more than 150 papers in reputable conferences and journals. He has won the best paper awards in several conferences and championships in international competitions. He has served as the area chair, senior PC or PC of many international conferences like CVPR, ICCV, AAAI, IJCAI. He is the associate editor or guest associate editor of Pattern Recognition, NeuroComputing, Pattern Recognition Letters, Cognitive Computation, IEEE Access and Frontiers of Computer Science. His contribution to this paper is the part of brain-like computer vision.
E-mail: zhaoxiang.zhang@ia.ac.cn|王威,1983年生,中国科学院自动化研究所,副研究员。2005年获武汉大学自动化专业学士学位,2011年获中国科学院大学计算机应用技术博士学位,同年加入中国科学院自动化研究所模式识别国家重点实验室。主要从事计算机视觉、认知计算的研究工作,目前研究主要集中在视觉认知机制计算建模、视觉语言协同理解。发表国际期刊和会议论文30多篇（包括TPAMI、TIP、TMM、NIPS、ICCV、CVPR等,其中CVPR2010他引200余次,CVPR2015他引760多次）,获得CVPR DeepVision Workshop 2014最佳论文奖、ICPR2014最佳学生论文奖,相关研究成果授权和申请专利10余项,主持国家自然科学基金项目（3项）、企业合作项目（国家电网、高德、富士通）等科研项目10余项。在本文中承担计算机视觉技术进展部分。
Wang Wei received his B.E. degree in Department of Automation from Wuhan University in 2005, and Ph.D. degree in University of Chinese Academy of Sciences in 2011. He is currently an associate professor in National Lab of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA). His research interests focus on computer vision and machine learning, particularly on the computational modelling of visual attention and memory, vision and language understanding. He has published more than thirty papers in refereed international journals and conferences such as TPAMI, TIP, CVPR, ICCV and NIPS. His contribution to this paper is the part of progress of computer vision.
E-mail: wei.wang@nlpr.ia.ac.cn|刘菲,1986年生,中国科学院自动化研究所智能感知与计算研究中心,博士后,2017年于中国科学院大学获得博士学位,主要研究方向为生物特征识别、计算成像、计算机视觉。在本文中参与第2章内容。
Liu Fei is a Postdoc in Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), China. She received the Ph.D. degree in University of Chinese Academy of Sciences in 2017. Her research focuses on biometrics, computational imaging and computer vision. Her contribution to this paper is the part of Section 2.
E-mail: fei.liu@nlpr.ia.ac.cn|谭铁牛,1964年生,中国科学院自动化研究所,研究员,中国科学院院士、发展中国家科学院院士、英国皇家工程院外籍院士、巴西科学院通讯院士、IEEE Fellow,主要研究方向为生物特征识别、模式识别、计算机视觉,出版著作11部,发表国际期刊和会议论文450篇。在本文负责论文总体架构和主要思路。
Tan Tieniu is currently a professor with the Center for Research on Intelligent Perception and Computing, NLPR, CASIA, China. He has published more than 450 research papers in refereed international journals and conferences in the areas of image processing, computer vision and pattern recognition, and has authored or edited 11 books. His research interests include biometrics, image and video understanding, information hiding, and information forensics. He is a fellow of the CAS, the TWAS, the BAS, the IEEE, the IAPR, the UK Royal Academy of Engineering, and the Past President of IEEE Biometrics Council. He is a fellow of the IEEE. His contribution to this paper include constructing manuscript structure and main ideas.
E-mail: tnt@nlpr.ia.ac.cn
基金资助:
国家自然科学基金国家重大科研仪器研制项目“复杂场景中多模态生物特征获取设备”(61427811)

Artificial Intelligence: Developments and Advances in 2019

Sun Zhenan^1,^2,^3,^*(),Zhang Zhaoxiang^1,^2,³,Wang Wei¹,Liu Fei¹,Tan Tieniu^1,^2,³

1. Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2. School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
3. CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing 100190, China

Received:2019-09-16 Online:2019-12-20 Published:2020-01-15
Contact: Sun Zhenan

摘要/Abstract

摘要：

【目的】人工智能已经成为社会各界最为关注的热点技术方向,本文旨在让政府部门、科技人员、产业人员和社会大众了解人工智能领域的最新动态。【方法】本文重点梳理了 2019 年人工智能新闻事件和科技文献,对人工智能领域总体发展态势进行概括和总结,对人工智能重点技术进展进行综述和展望。【结果】2019 年人工智能发展更加理性务实,一方面呈现出“瓜熟蒂落、水到渠成”的繁荣景象,在万物互联、大数据、超级计算、深度学习时代实现了技术应用和产业落地,另一方面我们也可以看到基于深度神经网络的技术创新开始进入平稳期,科研人员开始探索增强学习、自动化机器学习、脑机接口、类脑智能、可解释人工智能等新方向,在人工智能创新触发期“芽苞初放,生机勃勃”。【局限】本文以介绍人工智能技术进展为主,没有对技术未来方向进行全面预测。【结论】2019 年人工智能在神经形态芯片、脑机融合、人机博弈、智能机器人、计算机视觉、自然语言理解等领域都取得重要技术进展,但是我们看到迈向通用人工智能仍然任重道远,人工智能领域亟待革命性的技术创新和突破。

关键词: 人工智能, 计算机视觉, 神经形态芯片, 脑智融合, 智能机器人

Abstract:

[Objective] Artificial Intelligence (AI) has become a hot technology topic in the society. This paper aims to provide updated information of AI developments and advances to government, research community, industry and public. [Methods] This paper mainly reviews AI news and scientific publications in 2019 to summarize the overall technology progresses of AI. [Results] The AI community has become more rational and pragmatic relatively in 2019. On one hand, AI technologies are getting mature with more and more successful applications in the era of Internet of Things, Big Data, Super-computing, and Deep Learning. On the other hand, there are more and more promising and new directions in AI researches such as reinforcement learning, automatic machine learning, brain-machine interface, brain-like intelligence, and interpretable artificial intelligence. [Limitations] This paper mainly introduces the current development status of AI with limited efforts in prediction of future AI directions. [Conclusions] Great progress has been achieved in the areas of neuromorphic chips, brain-machine interface, human-computer game, intelligent robot, natural language understanding, and computer vision in 2019. But it is still a challenging task towards general AI. Technology breakthroughs are needed to achieve a new generation of AI.

Key words: artificial intelligence, computer vision, neuromorphic chips, brain-machine integrated intelligence, intelligent robot

孙哲南,张兆翔,王威,刘菲,谭铁牛. 2019 年人工智能新态势与新进展[J]. 数据与计算发展前沿, 2019, 1(2): 1-16.

Sun Zhenan,Zhang Zhaoxiang,Wang Wei,Liu Fei,Tan Tieniu. Artificial Intelligence: Developments and Advances in 2019[J]. Frontiers of Data and Computing, 2019, 1(2): 1-16.

参考文献 90

[1]	Gartner. 2019世界人工智能技术趋势分析报告[R]. 2019.8.
[2]	中国信息通信研究院, 中国人工智能产业发展联盟, 全球人工智能战略与政策观察（2019）[R]. 2019.8.
[3]	Intel’s Pohoiki Beach, a 64-Chip Neuromorphic System, Delivers Breakthrough Results in Research Tests [EB/OL]. [2019-7-15].https://newsroom.intel.com/news/intels-pohoiki-beach-64-chip-neuromorphic-system-delivers-breakthrough-results-research-tests/#gs.1pqqma.
[4]	Jing Pei, Lei Deng, Sen Song, Mingguo Zhao, Youhui Zhang, Shuang Wu, Guanrui Wang, Zhe Zou, Zhenzhi Wu, Wei He, Feng Chen, Ning Deng, Si Wu, Yu Wang, Yujie Wu, Zheyu Yang, Cheng Ma, Guoqi Li, Wentao Han, Huanglong Li, Huaqiang Wu, Rong Zhao, Yuan Xie, Luping Shi . Towards artificial general intelligence with hybrid Tianjic chip architecture[J]. Nature, 2019,572:106-111.
[5]	Elon Musk , Neurolink. An integrated brain-machine interface platform with thousands of channels[J]. bioRxiv 703801, 2019. Doi: https://doi.org/10.1101/703801.
[6]	Gopala K, Anumanchipalli, Josh Chartier, Edward F. Chang . Speech synjournal for neural decoding of spoken sentences[J]. Nature, 2019,568:493-498.
[7]	David A. Moses, Matthew K. Leonard, Joseph G. Makin, Edward F. Chang . Real-time decoding of question-and-answer speech dialogue using human cortical activity[J]. Nature Communications, 2019, 10, Article number: 3096.
[8]	Nathan Benaich and Ian Hogarth . State of AI 2019. https://www.stateof.ai/.
[9]	Noam Brown, Tuomas Sandholm . Superhuman AI for multiplayer poker[J]. Sciences, 2019,365(6456):885-890.
[10]	Guang-Zhong Yang, Robert J. Full, Neil Jacobstein, Peer Fischer, James Bellingham, Howie Choset, Henrik Christensen, Paolo Dario, Bradley J. Nelson, Russell Taylor. Ten robotics technologies of the year[J]. Science Robotics, 2019,4(26).
[11]	Atlas [EB/OL]. [2019].https://www.bostondynamics.com/atlas.
[12]	Shuguang Li, Richa Batra, David Brown, Hyun-Dong Chang, Nikhil Ranganathan, Chuck Hoberman, Daniela Rus, Hod Lipson . Particle robotics based on statistical mechanics of loosely coupled components[J]. Nature, 2019,567:361-365.
[13]	Zhenishbek Zhakypov, Kazuaki Mori, Koh Hosoda, Jamie Paik . Designing minimal and scalable insect-inspired multi-locomotion millirobots[J]. Nature, 2019,571:381-386.
[14]	Subramanian Sundaram, Petr Kellnhofer, Yunzhu Li, Jun-Yan Zhu, Antonio Torralba, Wojciech Matusik . Learning the signatures of the human grasp using a scalable tactile glove[J]. Nature, 2019,569:698-702.
[15]	Noah T. Jafferis E. Farrell Helbling, Michael Karpelson, Robert J. Wood . Untethered flight of an insect-sized flapping-wing microscale aerial vehicle[J]. Nature, 2019,570:491-495.
[16]	Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[C]. https://arxiv.org/abs/1810.04805, 2018.
[17]	Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le . XLNet: Generalized Autoregressive Pretraining for Language Understanding[C]. https://arxiv.org/abs/1906.08237, 2019.
[18]	Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov . RoBERTa: A Robustly Optimized BERT Pretraining Approach[C]. https://arxiv.org/abs/1907.11692, 2019.
[19]	Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Hao Tian, Hua Wu, Haifeng Wang . ERNIE 2.0: A Continual Pre-training Framework for Language Understanding[C]. https://arxiv.org/abs/1907.12412, 2019.
[20]	S. Xie, Z. Tu . Holistically-Nested Edge Detection[C]. International conference on computer vision (ICCV), 2015: 1395-1403.
[21]	J. Long, E. Shelhamer, T. Darrell . Fully Convolutional Networks for Semantic Segmentation[C]. International conference on computer vision and pattern recognition (CVPR), 2015: 3431-3440.
[22]	K. He, X. Zhang, S. Ren, J. Sun . Residual Learning for Image Recognition[C]. International conference on computer vision and pattern recognition (CVPR), 2016: 770-778.
[23]	R. Girshick, J. Donahue, T. Darrell, J. Malik . Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]. International conference on computer vision and pattern recognition (CVPR), 2014: 580-587.
[24]	C. Lu, R. Krishna, M. Bernstein, Fei-Fei Li . Visual Relationship Detection with Language Priors[C]. European conference on computer vision (ECCV), 2016: 852-869.
[25]	K. Simonyan, A. Zisserman . Two-stream convolutional networks for action recognition in videos[C]. Neural information processing systems (NIPS), 2014: 568-576.
[26]	C. Si, W. Chen, W. Wang, L. Wang, T. Tan . An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition[C]. International conference on computer vision and pattern recognition (CVPR), 2019: 1227-1236.
[27]	W. Wang, Y. Huang, L. Wang . Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model[C]. International conference on computer vision and pattern recognition (CVPR), 2019: 334-343.
[28]	Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz . SPLATNet: Sparse Lattice Networks for Point Cloud Processing[C]. International conference on computer vision and pattern recognition (CVPR), 2018: 2530-2539.
[29]	Xu K, Ba J, Kiros R, et al. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention[C]. International conference on machine learning (ICML), 2015: 2048-2057.
[30]	J. Wang, W. Wang, Y. Huang, L. Wanng, T. Tan . M3: Multimodal Memory Modelling for Video Captioning[C]. International conference on computer vision and pattern recognition (CVPR), 2018: 7512-7520.
[31]	Y. Aystar et al. SoundNet: Learning Sound Represen-tations from Unlabeled Video[C]. Neural information processing systems (NIPS), 2016: 892-900.
[32]	M.A. Lee, Y. Zhu, K. Srinivasan, P. Shah, S. Savarese, Li Fei-Fei, A. Garg, J. Bohg . Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks[C]. International conference on robotics and automation (ICRA), 2019.
[33]	M. Savva . et al. Habitat: A Platform for Embodied AI Research[C]. International conference on computer vision (ICCV), 2019.
[34]	X. Wang . et al. Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation[C]. International conference on computer vision and pattern recognition (CVPR), 2018: 6629-6638.
[35]	Goodfellow I J, Pougetabadie J, Mirza M, et al. Generative Adversarial Nets[C]. Neural information processing systems (NIPS), 2014: 2672-2680.
[36]	Salimans T, Goodfellow I J, Zaremba W, et al. Improved techniques for training GANs[C]. Neural information processing systems (NIPS), 2016: 2234-2242.
[37]	Isola P, Zhu J, Zhou T, et al. Image-to-Image Translation with Conditional Adversarial Networks[C]. International conference on computer vision and pattern recognition (CVPR), 2017: 5967-5976.
[38]	Ho J, Ermon S . Generative Adversarial Imitation Learning[C]. Neural information processing systems (NIPS), 2016: 4565-4573.
[39]	Arjovsky M, Chintala S, Bottou L, et al. Wasserstein Generative Adversarial Networks[C]. International conference on machine learning (ICML), 2017: 214-223.
[40]	Zhao J., Mathieu M., LeCun Y. Energy-based generative adversarial network[C]. https://arxiv.org/abs/1609.03126, 2016.
[41]	Zhu J, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]. International conference on computer vision (ICCV), 2017: 2242-2251.
[42]	Heusel M, Ramsauer H, Unterthiner T, et al. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium[C]. Neural information processing systems (NIPS), 2017: 6626-6637.
[43]	Huang H, Li Z, He R, et al. IntroVAE: Introspective Variational Autoencoders for Photographic Image Synconfproc[C]. Neural information processing systems (NIPS), 2018: 52-63.
[44]	Huang H, He R, Sun Z , et al. Wavelet Domain Generative Adversarial Network for Multi-scale Face Hallucination[J]. International Journal of Computer Vision (IJCV), 2019: 763-784.
[45]	Cao J, Hu Y, Zhang H, et al. Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization[C]. Neural information processing systems (NIPS), 2018: 2867-2877.
[46]	Jie Cao, Yibo Hu, Hongwen Zhang, Ran He, Zhenan Sun. Towards High Fidelity Face Frontalization in the Wild[J], International Journal of Computer Vision (IJCV), 2019, Accepted.
[47]	Huang H., He R., Sun Z., Tan T . Wavelet Domain Generative Adversarial Network for Multi-scale Face Hallucination[J]. International Journal of Computer Vision (IJCV), 2019,127(6-7):763-784.
[48]	Liu Y., Li Q., & Sun Z . Attribute-Aware Face Aging with Wavelet-Based Generative Adversarial Networks[C]. IEEE Conference on computer vision and pattern recognition (CVPR), 2019: 11877-11886.
[49]	Srivastava N, Hinton G E, Krizhevsky A , et al. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014,15(1):1929-1958.
[50]	Zhao G, Wang J, Zhang Z, et al. Random Shifting for CNN: A solution to reduce information loss in down-sampling layers[C]. International joint conference on artificial intelligence (IJCAI), 2017: 3476-3482.
[51]	Sabour S, Frosst N, Hinton G E, et al. Dynamic Routing Between Capsules[C]. Neural information processing systems (NIPS), 2017: 3856-3866.
[52]	Zhu G. Zhang Z. Zhang X. Liu C. . Diverse neuron type selection for convolutional neural networks[C]. International Joint Conference on Artificial Intelligence (AAAI), 2017: 3560-3566.
[53]	Zhang X S. Gao S. B. Li R X. Du X. Y. Li C. Y. Li Y. J. A retinal mechanism inspired color constancy model[J]. IEEE Transactions on Image Processing (TIP), 2016,25(3):1219-1232.
[54]	Li Y. Li C . A color-opponency based biological model for color constancy. I -Perception, 2011,2(4):384-384.
[55]	Gao S. Li Y . A retinal mechanism based color constancy model[C]. Chinese Conference on Pattern Recognition, 2012: 422-429.
[56]	Li Y. Chen Y. Wang N. Zhang Z. Scale-aware trident networks for object detection[C]. International conference on computer vision (ICCV), 2019.
[57]	Jim M. David L. G . Multiclass object recognition with sparse, localized features[C]. International Conference on computer vision and pattern recognition (CVPR), 2006: 11-18.
[58]	Wallis G Rolls E. T . A model of invariant object recognition in the visual system[J]. Progress in Neurobiology, 1997,51, 167-194.
[59]	LeCun Y. Boser B. Denker J. S. Backpropagation applied to handwritten zip code recognition[J]. Neural computation, 1989,1(4):541-551.
[60]	Krizhevsky A. Sutskever I. Hinton G . Imagenet classification with deep convolutional neural networks[C]. Neural information processing systems (NIPS), 2012,141(5):1097-1105.
[61]	Simonyan K, Zisserman A . Very Deep Convolutional Networks for Large-Scale Image Recognition[C]. International conference on learning representations (ICLR), 2015.
[62]	Szegedy C. Liu W. Jia Y. Sermanet P. Reed S. Anguelov D. Erhan D. Vanhoucke V. Rabinovich A . Going deeper with convolutions[C]. International Conference on computer vision and pattern recognition (CVPR), 2015: 1-9.
[63]	Shi T. Liang M. Hu X . A reverse hierarchy model for predicting eye fixations[C]. International conference on computer vision and pattern recognition (CVPR), 2014: 2822-2829.
[64]	Hochstein S, Ahissar M . View from the Top: Hierarchies and Reverse Hierarchies in the Visual System[J]. Neuron, 2002,36(5):791-804.
[65]	Liang M. Hu X . Recurrent convolutional neural network for object recognition[C]. International Conference on computer vision and pattern recognition (CVPR), 2015: 3367-3375.
[66]	Yoo D. Park S. Lee J Y. Paek A S. So Kweon I . Attentionnet: Aggregating weak directions for accurate object detection[C]. International conference on computer vision and pattern recognition (CVPR), 2015: 2659-2667.
[67]	En Q. Duan L. Zhang Z. Bai X. Zhang Y. Human-Like Delicate Region Erasing Strategy for Weakly Supervised Detection[C]. National Conference on Artificial Intelligence (AAAI), 2019,33:3502-3509.
[68]	Fang Y. Ma Z. Zhang Z . Dynamic multi-task learning with convolutional neural network[C]. International joint conference on artificial intelligence (IJCAI), 2017: 19-25.
[69]	Hao W. Zhang Z. Guan H . Integrating both Visual and Audio Cues for Enhanced Video Caption[C]. National Conference on Artificial Intelligence (AAAI), 2018: 6894-6901.
[70]	Hao W. Zhang Z. Guan H . CMCGAN: A Uniform Framework for Cross-Modal Visual-Audio Mutual Generation[C]. National Conference on Artificial Intelligence (AAAI), 2018: 6886-6893.
[71]	Dong W. Zhang Z. Tan T . Attention-Aware Sampling via Deep Reinforcement Learning for Action Recognition [C]. National Conference on Artificial Intelligence (AAAI), 2019,33:8247-8254.
[72]	Yang H. M. Zhang X. Y. Yin F. Liu C. L. Robust Classification with Convolutional Prototype Learning [C]. International conference on computer vision and pattern recognition, 2018: 3474-3482.
[73]	Chen Y, Wang N, Zhang Z . DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer[C]. National Conference on Artificial Intelligence (AAAI), 2018: 2852-2859.
[74]	Rusu A. A. Rabinowitz N. C. Desjardins G. Soyer H. Kirkpatrick J. Kavukcuoglu K. Hadsell R. Progressive neural networks[C]. arXiv preprint. arXiv:1606.04671, 2016.
[75]	Fernando C. Banarse D. Blundell C. Zwols Y. Ha D. Rusu A. A. Wierstra D. Pathnet: Evolution channels gradient descent in super neural networks[C]. arXiv preprint. arXiv:1701.08734, 2017.
[76]	Kirkpatrick J, Pascanu R, Rabinowitz N C , et al. Overcoming catastrophic forgetting in neural networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2017,114(13):3521-3526.
[77]	Lake B M. Salakhutdinov R. Tenenbaum J B. Human-level concept learning through probabilistic program induction[J]. Science, 2015,350(6266):1332-1338.
[78]	Friston K J, Adams R A, Perrinet L U , et al. Perceptions as Hypotheses: Saccades as Experiments[J]. Frontiers in Psychology, 2012: 151.
[79]	Lu Y. Yin J. Chen Z. Gong H. Liu Y. Qian L. Li X. Liu R. Andolina IM. Wang W. Revealing Detail along the Visual Hierarchy: Neural Clustering Preserves Acuity from V1 to V4[J]. Neuron, 2018,98(2):417-428.
[80]	Groen I. Silson E. Baker C. Contributions of low- and high-level properties to neural processing of visual scenes in the human brain[J]. Philosophical Transactions of the Royal Society B, 2017: 1-11.
[81]	Mackey W E, Winawer J, Curtis C E , et al. Visual field map clusters in human frontoparietal cortex[J]. eLife, 2017.
[82]	Markov N. Misery P. Falchier A. Lamy C. Vezoli J. Quilodran R. Gariel MA. Giroud P. Ercsey-Ravasz M. Pilaz LJ. Huissoud C. Barone P. Dehay C. Toroczkai Z. Van Essen DC. Kennedy H. Knoblauch K. Weight consistency specifies regularities of macaque cortical networks. Cerebral Cortex, 2011,21(6):1254-1272.
[83]	Lotter W. Kreiman G. Cox D . A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception[C]. arXiv preprint. arXiv:1805.10734, 2018.
[84]	O’Reilly R. C. Wyatte D. R. Rohrlich J . Deep Predictive Learning: A Comprehensive Model of Three Visual Streams[C]. arXiv preprint. arXiv:1709.04654, 2017.
[85]	Chong E, Familiar A, Shim W M , et al. Reconstructing representations of dynamic visual objects in early visual cortex[J]. Proceedings of the National Academy of Sciences of the United States of America, 2016,113(5):1453-1458.
[86]	Lawrence S. van Mourik T. Kok P. Koopmans P. Norris D. de Lange F . Laminar Organization of Working Memory Signals in Human Visual Cortex. Current biology, CB, 2018,28(21):3435-3440.
[87]	Petro L S, Paton A, Muckli L , et al. Contextual modulation of primary visual cortex by auditory signals[J]. Philosophical Transactions of the Royal Society B, 2017,372(1714).
[88]	Williams M. Baker C. Op de Beeck H. Mok Shim W. Dang S. Triantafyllou C Kanwisher N . Feedback of visual object information to foveal retinotopic cortex[J]. Nature Neuroscience, 2008,11(12):1439-1445.
[89]	Wyatte D. Curran T. O ˛a´ rReilly R . The limits of feedforward vision: recurrent processing promotes robust object recognition when objects are degraded[J]. Journal of Cognitive Neuroscience, 2012,24(11), 2248-2261.
[90]	Roelfsema P. de Lange F . Early Visual Cortex as a Multiscale Cognitive Blackboard [R]. Annual Review of Vision Science, 2016,2(1):131-151.

2019 年人工智能新态势与新进展

Artificial Intelligence: Developments and Advances in 2019

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 90

相关文章 13

编辑推荐

Metrics

本文评价

[1]	刘嘉琪,杨斌艳. 我国人工智能与社会科学耦合发展的热点与趋势研究——基于CiteSpace的文献计量分析[J]. 数据与计算发展前沿, 2022, 4(6): 77-91.
[2]	陈琼,杨咏,黄天林,冯媛. 小样本图像语义分割综述[J]. 数据与计算发展前沿, 2021, 3(6): 17-34.
[3]	张润滋,刘文懋. AISecOps智能安全运营技术体系框架[J]. 数据与计算发展前沿, 2021, 3(3): 32-47.
[4]	袁勇,欧阳丽炜,王晓,王飞跃. 基于区块链的智能组件：一种分布式人工智能研究新范式[J]. 数据与计算发展前沿, 2021, 3(1): 1-14.
[5]	莫梓嘉,高志鹏,苗东. 边缘智能：人工智能向边缘分布式拓展的新触角[J]. 数据与计算发展前沿, 2020, 2(4): 16-27.
[6]	喻鹏,李文璟,丰雷,周凡钦,杨杨,邱雪松. 面向未来6G网络的智能管控架构与关键技术[J]. 数据与计算发展前沿, 2020, 2(3): 32-44.
[7]	李肯立,阳王东,陈岑,陈建国,丁岩. 面向人工智能和大数据的高效能计算[J]. 数据与计算发展前沿, 2020, 2(1): 27-37.
[8]	唐川,秦小林,李若男,王会勇. 国际人工智能研究前沿及演进趋势——基于对人工智能期刊论文的突变术语探测分析[J]. 数据与计算发展前沿, 2019, 1(2): 121-134.
[9]	王彦棡,王珏,曹荣强. 人工智能计算与数据服务平台的研究与应用[J]. 数据与计算发展前沿, 2019, 1(2): 86-97.
[10]	廖方宇,洪学海,汪洋,褚大伟. 数据与计算平台是驱动当代科学研究发展的重要基础设施[J]. 数据与计算发展前沿, 2019, 1(1): 2-10.
[11]	马艳军,于佃海,吴甜,王海峰. 飞桨：源于产业实践的开源深度学习平台[J]. 数据与计算发展前沿, 2019, 1(1): 105-115.
[12]	康波,夏梓峻,孟祥飞. 应用驱动的大数据与人工智能融合平台建设[J]. 数据与计算发展前沿, 2019, 1(1): 35-45.
[13]	苏萌,贾喜顺,杜晓梦,高体伟. 数据中台技术相关进展及发展趋势[J]. 数据与计算发展前沿, 2019, 1(1): 116-126.