Deep Learning for AI

被引：345
作者：
Bengio, Yoshua [1 ]
Lecun, Yann [2 ,3 ,4 ]
Hinton, Geoffrey [5 ,6 ,7 ]
机构：
[1] Univ Montreal, Dept Comp Sci & Operat Res, Montreal, PQ, Canada
[2] Facebook, Menlo Pk, CA USA
[3] New York Univ, Courant Inst Math Sci, New York, NY USA
[4] New York Univ, Ctr Data Sci, New York, NY USA
[5] Vector Inst, Toronto, ON, Canada
[6] Google, Mountain View, CA 94043 USA
[7] Univ Toronto, Comp Sci, Toronto, ON, Canada
来源：
COMMUNICATIONS OF THE ACM | 2021年 / 64卷 / 07期
关键词：
NEURAL-NETWORKS;
D O I：
10.1145/3448250
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
RESEARCH ON ARTIFICIAL neural networks was motivated by the observation that human intelligence emerges from highly parallel networks of relatively simple, non-linear neurons that learn by adjusting the strengths of their connections. This observation leads to a central computational question: How is it possible for networks of this general kind to learn the complicated internal representations that are required for difficult tasks such as recognizing.
引用
收藏
页码：58 / 65
页数：8
相关论文
共 87 条
[41]  
Graves A., 2013, GENERATING SEQUENCES
[42]  
Grill J-B., 2020, AEXIV200607733
[43]  
Gutmann Michael, 2010, JMLRWORKSHOP C P, P297
[44]  
He K., 2020, ARXIV200304297
[45]  
He K., 2020, P CVPR 2020 JUN
[46]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[47]   Reducing the dimensionality of data with neural networks [J].
Hinton, G. E. ;
Salakhutdinov, R. R. .
SCIENCE, 2006, 313 (5786) :504-507
[48]  
Hinton G.E., 2012, ARXIV
[49]   MAPPING PART-WHOLE HIERARCHIES INTO CONNECTIONIST NETWORKS [J].
HINTON, GE .
ARTIFICIAL INTELLIGENCE, 1990, 46 (1-2) :47-75
[50]   Deep Neural Networks for Acoustic Modeling in Speech Recognition [J].
Hinton, Geoffrey ;
Deng, Li ;
Yu, Dong ;
Dahl, George E. ;
Mohamed, Abdel-rahman ;
Jaitly, Navdeep ;
Senior, Andrew ;
Vanhoucke, Vincent ;
Patrick Nguyen ;
Sainath, Tara N. ;
Kingsbury, Brian .
IEEE SIGNAL PROCESSING MAGAZINE, 2012, 29 (06) :82-97
123456789