AutoDL Challenge Design and Beta Tests-Towards automatic deep learning

International audienceFollowing the success of the first AutoML challenges , we designed a new challenge called AutoDL. We target applications such as speech, image, video, and text, for which deep learning (DL) methods have had great success in the past few years. All problems will be multi-label classification problems. We hope to drive the community to work on finding fully automatic ways of designing DL models. Raw data will be provided (no features extracted). The source of the datasets and the type of data will be concealed, but the data structure will be revealed. All datasets will be formatted in a uniform tensor manner, to encourage participants to submit generic algorithms (not necessarily constrained to DL). We will impose restrictions on training time and resources to push the state-of-the-art further. We will provide a large number of pre-formatted public datasets and set up a repository of data exchange to enable meta-learning. In this paper, the challenge protocol and baseline results are presented to seek community feed-back. The challenge is planned for 2019, but the exact schedule is not announced yet