Adrien Gaidon — Advancing ML Research in Autonomous Vehicles
Adrien Gaidon — Advancing ML Research in Autonomous Vehicles  
Podcast: Gradient Dissent: Conversations on AI
Published On: Thu Apr 22 2021
Description: Adrien Gaidon shares his approach to building teams and taking state-of-the-art research from conception to production at Toyota Research Institute.---Adrien Gaidon is the Head of Machine Learning Research at the Toyota Research Institute (TRI). His research focuses on scaling up ML for robot autonomy, spanning Scene and Behavior Understanding, Simulation for Deep Learning, 3D Computer Vision, and Self-Supervised Learning. Connect with Adrien:Twitter: https://twitter.com/adnothingLinkedIn: https://www.linkedin.com/in/adrien-gaidon-63ab2358/Personal website: https://adriengaidon.com/---Topics Discussed:0:00 Sneak peek, intro0:48 Guitars and other favorite tools3:55 Why is PyTorch so popular?11:40 Autonomous vehicle research in the long term15:10 Game-changing academic advances20:53 The challenges of bringing autonomous vehicles to market26:05 Perception and prediction35:01 Fleet learning and meta learning41:20 The human aspects of machine learning44:25 The scalability bottleneckTranscript:http://wandb.me/gd-adrien-gaidonLinks Discussed:TRI Global Research: https://www.tri.global/research/todoist: https://todoist.com/Contrastive Learning of Structured World Models: https://arxiv.org/abs/2002.05709SimCLR: https://arxiv.org/abs/2002.05709---Get our podcast on these platforms:Apple Podcasts: http://wandb.me/apple-podcasts​​Spotify: http://wandb.me/spotify​Google Podcasts: http://wandb.me/google-podcasts​​YouTube: http://wandb.me/youtube​​Soundcloud: http://wandb.me/soundcloud​Join our community of ML practitioners where we host AMAs, share interesting projects and meet other people working in Deep Learning:http://wandb.me/slack​​Check out Fully Connected, which features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, industry leaders sharing best practices, and more:https://wandb.ai/fully-connected