Home
(Automated Deep Learning)
News:
Analysis of the AutoML Challenge series 2015-2018 Isabelle Guyon, Lisheng Sun-Hosoya, Marc Boullé, Hugo Escalante, Sergio Escalera, Zhengying Liu, Damir Jajetic, Bisakha Ray, Mehreen Saeed, Michèle Sebag, et al. in Automated Machine Learning pp 177–219, Springer, 2019 [BIBTEX]
Finished: KDDCup - AutoML on temporal relational data [Competition]
Upcoming Spring 2019
AutoDL challenge [SIGN UP]
December 7, 2019
Competition Workshop at NeurIPS 2019
August 28, 2018
We had a workshop at PRICAI 2018.
July 14-15 2018:
We had a nice workshop at ICML 2018.
March 2018:
Our next competition on Life Long ML is accepted to NIPS 2018.
June 21, 2016: Microsoft published a BLOG post on AutoML 1.
We re-implemented old challenges in Codalab [NIPS 2003][KDDcup 2009, small, large] and created one for [MNIST data]
Some older "news":
AutoML 8 (Automatic Natural Language Processing = AutoNLP), AutoML 7 (Automatic Computer Vision 2 = AutoC2) , AutoML 6 (Automatic Computer Vision = AutoCV), part of the AutoDL series, 28,000 USD in prizes.
AutoML5 : KDDCup2019 - AutoML for Temporal Relational Data
30,000USD+ in prizes
Competition session at PAKDD2019
Welcome to AutoML@ChaLearn. ChaLearn is a non-for-profit organization bringing to you challenges and workshops in Machine Learning. The AutoML track works since 2014 to stimulate the community to work on the problem of creating ML algorithms that work without any human intervention. This means completely automatically choosing models, architectures, hyper-parameters, etc. There are statistical challenges (not over-fitting) and computational challenges (searching fast a large space of possibilities).
ChaLearn also has a very active Computer Vision track.