扬·勒丘恩

维基百科,自由的百科全书
跳转至: 导航搜索
扬·勒丘恩
Yann LeCun at the University of Minnesota.jpg
出生 (1960-07-08) 1960年7月8日(57歲)
机构 New York University
Facebook Artificial Intelligence Research
母校 Pierre and Marie Curie University
論文 Modeles connexionnistes de l'apprentissage (connectionist learning models)(1987)
博士導師 Maurice Milgram
知名于 Deep learning
網站
yann.lecun.com

扬·勒丘恩(法语:Yann Le Cun英语:Yann LeCun,1960年7月8日—)是一位计算机科学家,他在机器学习计算机视觉、mobile robotics和計算神經科學等领域都有很多贡献。他最著名的工作是在光学字符识别计算机视觉上使用卷积神经网络 (CNN),他也被称为卷积网络之父。[1][2]他同Léon Bottou和Patrick Haffner等人一起创建了DjVu图像压缩技术。他同Léon Bottou一起开发了Lush语言。

生平[编辑]

扬·勒丘恩于1960年生于法国巴黎附近。他1983年从位于巴黎的Ecole Superieure d'Ingénieur en Electrotechnique et Electronique (ESIEE), 获得了一个Diplôme d'Ingénieur(工程师学位),1987年从巴黎第六大学获得了一个计算机科学博士学位。博士在学期间,他提出了神经网络的反向传播算法学习算法的原型。[3]他在杰弗里·辛顿的实验室做博士后,学校是多倫多大學

1988年,他加入了贝尔实验室的Adaptive Systems Research Department,位于美国新泽西州霍姆德爾鎮區。实验室的领导是Lawrence D. Jackel,在此,他开发了很多新的机器学习方法,比如图像识别的模型称为卷积神经网络,[4]"Optimal Brain Damage" regularization methods,[5]以及Graph Transformer Networks方法(类似于條件隨機域),他将其应用到手写识别和OCR中。[6] The bank check recognition system that he helped develop was widely deployed by NCR and other companies, reading over 10% of all the checks in the US in the late 1990s and early 2000s.

1996年,他加入了AT&T Labs-研究,成为Image Processing Research Department的领导,这个Department是 Lawrence Rabiner领导的Speech and Image Processing Research Lab的一部分,主要工作是DjVu图像压缩技术,[7] 被以互联网档案馆为首的网站使用,用来发布扫描的文档。他的AT&T同事包括Léon Bottou和弗拉基米尔·万普尼克

After a brief tenure as a Fellow of the NEC Research Institute (now NEC-Labs America) in 普林斯顿, he joined 纽约大学 (NYU) in 2003, where he is Silver Professor of Computer Science Neural Science at the 科朗数学研究所 and the Center for Neural Science. He is also a professor at the 纽约大学坦登工程学院.[8][9] At NYU, he has worked primarily on Energy-Based Models for supervised and unsupervised learning,[10] feature learning for object recognition in 计算机视觉,[11] and mobile robotics.[12]

2012年,他成为了NYU Center for Data Science的创建主任。[13] 2013年12月9日,勒丘恩成为位于纽约的Facebook AI Research的第一任主任,[14]2014年初期逐步退出了NYU-CDS的领导层。

勒丘恩获得了2014 IEEE Neural Network Pioneer Award和2015 PAMI Distinguished Researcher Award。

在2013年, 他和Yoshua Bengio一起创建了International Conference on Learning Representations, which adopted a post-publication open review process he previously advocated on his website. He was the chair and organizer of the "Learning Workshop" held every year between 1986 and 2012 in Snowbird, Utah. He is a member of the Science Advisory Board of the Institute for Pure and Applied Mathematics[15] at 加州大学洛杉矶分校, and has been on the advisory board of a number of companies, including MuseAmi, KXEN Inc., and Vidient Systems.[16] He is the Co-Director of the Neural Computation & Adaptive Perception research program of CIFAR[17]

在2016年,他在巴黎法兰西公学院的"Chaire Annuelle Informatique et Sciences Numériques"做访问教授。His "leçon inaugurale" (inaugural lecture) has been an important event in 2016 Paris intellectual life.

姓名[编辑]

扬·勒丘恩姓(Le Cun),到美国之后,很多人都误认为Le是中间名,所以他在20世纪八九十年代把自己的姓的拼法改成了LeCun[18][19]

参考[编辑]

  1. ^ Convolutional Nets and CIFAR-10: An Interview with Yann LeCun.
  2. ^ LeCun, Yann; Yoshua Bengio; Patrick Haffner. Gradient-based learning applied to document recognition (PDF). Proceedings of the IEEE. 1998, 86 (11): 2278–2324 [16 November 2013]. doi:10.1109/5.726791.  Authors list列表缺少|last2= (帮助)
  3. ^ Y. LeCun: Une procédure d'apprentissage pour réseau a seuil asymmetrique (a Learning Scheme for Asymmetric Threshold Networks), Proceedings of Cognitiva 85, 599–604, Paris, France, 1985.
  4. ^ Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard and L. D. Jackel: Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation, 1(4):541-551, Winter 1989.
  5. ^ Yann LeCun, J. S. Denker, S. Solla, R. E. Howard and L. D. Jackel: Optimal Brain Damage, in Touretzky, David (Eds), Advances in Neural Information Processing Systems 2 (NIPS*89), Morgan Kaufmann, Denver, CO, 1990.
  6. ^ Yann LeCun, Léon Bottou, Yoshua Bengio and Patrick Haffner: Gradient Based Learning Applied to Document Recognition, Proceedings of IEEE, 86(11):2278–2324, 1998.
  7. ^ Léon Bottou, Patrick Haffner, Paul G. Howard, Patrice Simard, Yoshua Bengio and Yann LeCun: High Quality Document Image Compression with DjVu, Journal of Electronic Imaging, 7(3):410–425, 1998.
  8. ^ People - Electrical and Computer Engineering. Polytechnic Institute of New York University. [13 March 2013]. 
  9. ^ http://yann.lecun.com/
  10. ^ Yann LeCun, Sumit Chopra, Raia Hadsell, Ranzato Marc'Aurelio and Fu-Jie Huang: A Tutorial on Energy-Based Learning, in Bakir, G. and Hofman, T. and Schölkopf, B. and Smola, A. and Taskar, B. (Eds), Predicting Structured Data, MIT Press, 2006.
  11. ^ Kevin Jarrett, Koray Kavukcuoglu, Marc'Aurelio Ranzato and Yann LeCun: What is the Best Multi-Stage Architecture for Object Recognition?, Proc.
  12. ^ Raia Hadsell, Pierre Sermanet, Marco Scoffier, Ayse Erkan, Koray Kavackuoglu, Urs Muller and Yann LeCun: Learning Long-Range Vision for Autonomous Off-Road Driving, Journal of Field Robotics, 26(2):120–144, February 2009.
  13. ^ http://cds.nyu.edu
  14. ^ https://www.facebook.com/yann.lecun/posts/10151728212367143
  15. ^ http://www.ipam.ucla.edu/programs/gss2012/ Institute for Pure and Applied Mathematics
  16. ^ Vidient Systems.
  17. ^ Neural Computation & Adaptive Perception Advisory Committee Yann LeCun. CIFAR. [16 December 2013]. 
  18. ^ No, Your Name can't possibly be pronounced that way.
  19. ^ La leçon d’un maître de l’intelligence artificielle au Collège de France.

外部链接[编辑]