Organizers: Hang Zhang, Matthias Seeger, Mu Li
In this tutorial, we design the hyper-parameter ranges and possible network architecture combinations in deep learning approaches, and pass the workload to the machines. This tutorial will cover the important concepts in automatic machine learning, andthe applications in computer vision. The audience will be able to reproduce large scale experimentsthrough hands-on section using Jupiter Notebooks.
Topic | Slides | Notebook |
---|---|---|
Opening and tutorial notebook setup | link | link, link |
Overview of AutoML and HPO | link, link | |
Advanced search algorithms | link | link, link |
Efficient neural architecture search | link | link |
Large scale distributed search | link | |
Q&A and Closing |