CVPR 2020 Tutorial onFrom HPO to NAS: Automated Deep Learning |
||
Online 06/15/2020 |
||
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 the applications in computer vision. The audience will be able to reproduce large scale experiments through hands-on section using Jupyter Notebooks.
Afternoon section, Jun 15, 2020 (PST)
Everyone can get a gpu machine for hands-on, please send any email to 
1:30 - 2:15 PM Automated HP and Architecture Tuning by Cédric Archambeau [Slides, YouTube, Bilibili]
2:15 - 2:45 PM Introducing AutoGluon Toolkit by Hang Zhang [Slides, YouTube, Bilibili]
3:00 - 3:45 PM AutoML for TinyML with Once-for-All Network by Song Han [Slides, YouTube, Bilibili]
3:45 - 4:45 PM Hands-on Section
Time in PST. Password: Seattle
06/15/2020 6:00 - 6:30 PM Q&A for AutoGluon Toolkit and NAS [join at zoom]
06/16/2020 8:00 - 8:30 AM Q&A for Advanced HPO Algorithm [join at zoom]
During CVPR Conference Offline Q&A[GoogleDoc]
Contact: Hang Zhang
