Challenges in Representation Learning: A report on three machine learning contests Ian J. Goodfellow 1 , Dumitru Erhan 2 , Pierre Luc Carrier, Aaron Courville, Mehdi Mirza, Ben Hamner, Will Cukierski, Yichuan Tang, David Thaler, Dong-Hyun Lee, Yingbo Zhou, Chetan Ramaiah, Fangxiang Feng, Ruifan Li, Xiaojie Wang, Dimitris Athanasakis, John Shawe-Taylor, Maxim Milakov, John Park, Radu Ionescu, Marius Popescu, Cristian Grozea, James Bergstra, Jingjing Xie, Lukasz Romaszko, Bing Xu, Zhang Chuang, and Yoshua Bengio 1 Universit´ e de Montr´ eal, Montr´ eal QC H3T 1N8, Canada, goodfeli@iro.umontreal.ca 2 Google, Venice, CA 90291, USA, dumitru@google.com Abstract. The ICML 2013 Workshop on Challenges in Representation Learning 3 focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learn- ing challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for or- ganizers of future challenges and some comments on what kind of knowl- edge can be gained from machine learning competitions. Keywords: representation learning, competition, dataset 1 Introduction This paper describes three machine learning contests that were held as part of the ICML workshop “Challenges in Representation Learning.” The purpose of the workshop, organized by Ian Goodfellow, Dumitru Erhan, and Yoshua Bengio, was to explore the latest developments in representation learning, with a special emphasis on testing the capabilities of current representation learning algorithms (See [1] for a recent review) and pushing the field towards new developments via these contests. Ben Hamner and Will Cukierski handled all issues related to Kaggle hosting and ensured that the contests ran smoothly. Google provided prizes for all three contests. The winner of each contest received $350 while the runner-up received $150. A diverse range of competitors spanning academia, industry, and amateur machine learning provided excellent solutions to all three problems. In this paper, we summarize their solutions, and discuss what we can learn from them. 2 The black box learning challenge 3 http://deeplearning.net/icml2013-workshop-competition arXiv:1307.0414v1 [stat.ML] 1 Jul 2013