Principal-Centric AI with Adrien Gaidon
EPISODE 575
|
MAY
23,
2022
Watch
Follow
Share
About this Episode
This week, we continue our conversations around the topic of Data-Centric AI joined by a friend of the show Adrien Gaidon, the head of ML research at the Toyota Research Institute (TRI). In our chat, Adrien expresses a fourth, somewhat contrarian, viewpoint to the three prominent schools of thought that organizations tend to fall into, as well as a great story about how the breakthrough came via an unlikely source. We explore his principle-centric approach to machine learning as well as the role of self-supervised machine learning and synthetic data in this and other research threads. Make sure you’re following along with the entire DCAI series at twimlai.com/go/dcai.
About the Guest
Adrien Gaidon
Toyota Research Institute
Resources
- Paper: Full Surround Monodepth from Multiple Cameras
- Paper: Self-Supervised Camera Self-Calibration from Video
- Paper: Self-supervised Learning is More Robust to Dataset Imbalance
- GitHub - TRI-ML/packnet-sfm: TRI-ML Monocular Depth Estimation Repository
- Juan Carlos Niebles
- Tengyu Ma
- Mixture-of-Experts and Trends in Large-Scale Language Modeling with Irwan Bello - #569
- 100x Improvements in Deep Learning Performance with Sparsity with Subutai Ahmad - #562
- A Universal Law of Robustness via Isoperimetry with Sebastian Bubeck - #551
- The Benefit of Bottlenecks in Evolving Artificial Intelligence with David Ha - #535
- Reinforcement Learning for Industrial AI with Pieter Abbeel - #476
- Advancing Autonomous Vehicle Development Using Distributed Deep Learning with Adrien Gaidon - #269
