Help Automating Deep Learning
Following the success of previous AutoML challenges, we designed a new challenge: AutoDL. We target applications such as speech, image, video, and text, for which deep learning (DL) methods have had great success recently, to drive the community to work on automating the design of DL models. Raw data will be provided, formatted in a uniform tensor manner, to encourage participants to submit generic algorithms. All problems will be multi-label classification problems. 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.