ECCV 2020 Tutorial onFrom HPO to NAS: Automated Deep Learning |
||
Online 08/28/2020 |
||
Researchers have spent tremendous time in optimizing hyper-parameters and tweaking architectures. Can we alleviate the efforts in developing deep learning algorithms and make the researchers focus more on innovative areas? In this tutorial, we encourage the researchers to design the hyper-parameter ranges and possible network architecture combinations, and pass the workload to the machines. This tutorial will cover the important concepts in automatic machine learning, and neural architecture search.
08:45 - 09:00 Quick Introduction and Tutorial Overview by Hang Zhang [slides, youtube]
09:00 - 09:45 Introduction to Neural Architecture Search for Computer Vision Linjie Yang [slides, youtube]
09:45 - 10:30 Hardware-aware Deep Neural Architecture Search Peizhao Zhang [slides, youtube]
10:30 - 11:00 Model-based Async HP and Neural Architecture Search by Matthias Seeger [slides, youtube]
11:00 - 11:30 Does Unsupervised Architecture Representation Learning Help NAS by Mi Zhang [slides, youtube]
11:30 - 12:00 AutoML for 3D Deep Learning by Zhijian Liu & Haotian Tang [slides, youtube]
Contact: Hang Zhang
