Challenges in representation learning: A report on three machine learning contests

被引：332

作者：

Goodfellow, Ian J. ^{[1
]}

Erhan, Dumitru ^{[2
]}

Carrier, Pierre Luc ^{[1
]}

Courville, Aaron ^{[1
]}

Mirza, Mehdi ^{[1
]}

Hamner, Ben ^{[3
]}

Cukierski, Will ^{[3
]}

Tang, Yichuan ^{[4
]}

Thaler, David

Lee, Dong-Hyun ^{[5
]}

Zhou, Yingbo ^{[6
]}

Ramaiah, Chetan ^{[6
]}

Feng, Fangxiang ^{[7
]}

Li, Ruifan ^{[7
]}

Wang, Xiaojie ^{[7
]}

Athanasakis, Dimitris ^{[8
]}

Shawe-Taylor, John ^{[8
]}

Milakov, Maxim

Park, John

Ionescu, Radu ^{[9
]}

Popescu, Marius ^{[9
]}

Grozea, Cristian ^{[10
]}

Bergstra, James ^{[11
]}

Xie, Jingjing ^{[7
]}

Romaszko, Lukasz

Xu, Bing ^{[7
]}

Chuang, Zhang ^{[7
]}

Bengio, Yoshua ^{[1
]}

机构：

[1] Univ Montreal, Montreal, PQ H3T 1N8, Canada

[2] Google, Venice, CA 90291 USA

[3] Kaggle, Chicago, IL USA

[4] Univ Toronto, Toronto, ON M5S 1A1, Canada

[5] Nangman Comp, Seoul, South Korea

[6] SUNY Buffalo, Buffalo, NY 14260 USA

[7] Beijing Univ Posts & Telecommun, Beijing, Peoples R China

[8] UCL, London WC1E 6BT, England

[9] Univ Bucharest, Bucharest, Romania

[10] VICOM, Singapore, Singapore

[11] Univ Waterloo, Waterloo, ON N2L 3G1, Canada

来源：

NEURAL NETWORKS | 2015年 / 64卷

关键词：

Representation learning; Competition; Dataset;

D O I：

10.1016/j.neunet.2014.09.005

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The ICML 2013 Workshop on Challenges in Representation Learning(1) focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers of future challenges and some comments on what kind of knowledge can be gained from machine learning competitions. (C) 2014 Elsevier Ltd. All rights reserved.

引用

页码：59 / 63

页数：5

共 50 条

[41] Open Challenges in Federated Machine Learning
Baresi, Luciano
Quattrocchi, Giovanni
Rasi, Nicholas
IEEE INTERNET COMPUTING, 2023, 27 (02) : 20 - 27
[42] Machine Learning in EDA: Opportunities and Challenges
Fallon, Elias
PROCEEDINGS OF THE 2020 ACM/IEEE 2ND WORKSHOP ON MACHINE LEARNING FOR CAD (MLCAD '20), 2020, : 103 - 103
[43] Machine learning in pharmacometrics: Opportunities and challenges
McComb, Mason
Bies, Robert
Ramanathan, Murali
BRITISH JOURNAL OF CLINICAL PHARMACOLOGY, 2022, 88 (04) : 1482 - 1499
[44] Representation learning based on hybrid polynomial approximated extreme learning machine
Tinghui Ouyang
Xun Shen
Applied Intelligence, 2022, 52 : 8321 - 8336
[45] Representation learning based on hybrid polynomial approximated extreme learning machine
Ouyang, Tinghui
Shen, Xun
APPLIED INTELLIGENCE, 2022, 52 (07) : 8321 - 8336
[46] MULTIMODAL REPRESENTATION LEARNING: ADVANCES, TRENDS AND CHALLENGES
Zhang, Su-Fang
Zhai, Jun-Hai
Xie, Bo-Jun
Zhan, Yan
Wang, Xin
PROCEEDINGS OF 2019 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), 2019, : 362 - 367
[47] Towards hybridization of knowledge representation and machine learning
Khorsi, Ahmed
COMPUTING AND INFORMATICS, 2007, 26 (02) : 123 - 147
[48] A review of molecular representation in the age of machine learning
Wigh, Daniel S.
Goodman, Jonathan M.
Lapkin, Alexei A.
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE, 2022, 12 (05)
[49] Unified representation of molecules and crystals for machine learning
Huo, Haoyan
Rupp, Matthias
MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2022, 3 (04):
[50] Scale-invariant representation of machine learning
Lee, Sungyeop
Jo, Junghyo
PHYSICAL REVIEW E, 2022, 105 (04)

← 1 2 3 4 5 →