Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

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

: Goodfellow, Ian J.; Erhan, Dumitru; Carrier, Pierre Luc; Courville, Aaron C.; Mirza, Mehdi; Hamner, Benjamin; Cukierski, William; Tang, Yichuan; Thaler, David; Lee, Dong-Hyun; Zhou, Yingbo; Ramaiah, Chetan; Feng, Fangxiang; Li, Ruifan; Wang, Xiaojie; Athanasakis, Dimitris; Shawe-Taylor, John; Milakov, Maxim; Park, John; Ionescu, Radu-Tudor; Popescu, Marius; Grozea, Cristian; Bergstra, James; Xie, Jingjing; Romaszko, Lukasz; Xu, Bing; Zhang, Chuang; Bengio, Yoshua


Lee, M.:
Neural information processing. 20th International Conference, ICONIP 2013. Vol.3 : Daegu, Korea, November 3-7, 2013; Proceedings
Berlin: Springer, 2013 (Lecture Notes in Computer Science 8228)
ISBN: 978-3-642-42050-4 (Print)
ISBN: 978-3-642-42051-1 (Online)
ISBN: 3-642-42050-8
International Conference on Neural Information Processing (ICONIP) <20, 2013, Daegu/Korea>
Conference Paper
Fraunhofer FOKUS ()
machine learning; challenge; face recognition; computer vision

The ICML 2013 Workshop on Challenges in Representation Learning 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.