Liam Li

Developer, Determined AI

I recently completed my PhD in Machine Learning from Carnegie Mellon University, where I was advised by Ameet Talwalkar. My thesis was on efficient methods for automating machine learning model to make the practice of machine learning easier and more accessible.

Since then, I’ve joined Determined AI as a machine learning engineer to build the leading platform for deep learning, enabling users to be vastly more productive and happier! Post PhD, I continue to be involved in the AutoML community and am working with folks to organize the 2nd ICLR workshop on Neural Architecture Search. I also like to stay on top of exciting discoveries in machine learning and diving into areas of ML that I didn’t get to learn more about during my PhD.

Past sessions

Summit 2021 Object Detection with Transformers

May 26, 2021 04:25 PM PT

Object Detection with Transformers: From Training to Deployment with Determined AI and MLflow

Object detection is a central problem in computer vision and underpins many applications from medical image analysis to autonomous driving. In this talk, we will review the basics of object detection from fundamental concepts to practical techniques. Then, we will dive into cutting-edge methods that use transformers to drastically simplify the object detection pipeline while maintaining predictive performance.  Finally, we will show how to train these models at scale using Determined's integrated deep learning platform and then serve the models using MLflow.

What you will learn:

  • Basics of object detection including main concepts and techniques
  • Main ideas from the DETR and Deformable DETR approaches to object detection
  • Overview of the core capabilities of Determined’s deep learning platform, with a focus on its support for effortless distributed training
  • How to serve models trained in Determined using MLflow
In this session watch:
Liam Li, Developer, Determined AI

[daisna21-sessions-od]