Adrien Gaidon's guest appearances

Adrien Gaidon

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Gradient Dissent: Exploring Machine Learning, AI, Deep Learning, Computer Vision

Sean Taylor

Xavier Amatriain

Josh Bloom

Richard Socher

Hamel Husain

Josh Tobin

Bharath Ramsundar

Ion Stoica

Kathryn Hume

Pieter Abbeel

Jeremy Howard

Suzana Ilić

Angela Bassa

Daphne Koller

Drago Anguelov

OwlTail

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.The complete show notes for this episode can be found at twimlai.com/go/575

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 <a href="twimlai.com/go/dcai" rel="nofollow" target="_blank">twimlai.com/go/dcai</a>.The complete show notes for this episode can be found at <a href="twimlai.com/go/575" rel="nofollow" target="_blank">twimlai.com/go/575</a>

Principle-centric AI with Adrien Gaidon - #575

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

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: <a href="https://twitter.com/adnothing" rel="nofollow" target="_blank">https://twitter.com/adnothing</a> ﻿﻿﻿LinkedIn﻿: <a href="https://www.linkedin.com/in/adrien-gaidon-63ab2358/" rel="nofollow" target="_blank">https://www.linkedin.com/in/adrien-gaidon-63ab2358/</a> Personal website: <a href="https://adriengaidon.com/" rel="nofollow" target="_blank">https://adriengaidon.com/</a> --- Topics Discussed: 0:00 Sneak peek, intro 0:48 Guitars and other favorite tools 3:55 Why is PyTorch so popular? 11:40 Autonomous vehicle research in the long term 15:10 Game-changing academic advances 20:53 The challenges of bringing autonomous vehicles to market 26:05 Perception and prediction 35:01 Fleet learning and meta learning 41:20 The human aspects of machine learning 44:25 The scalability bottleneck Transcript: <a href="http://wandb.me/gd-adrien-gaidon" rel="nofollow" target="_blank">http://wandb.me/gd-adrien-gaidon</a> Links Discussed: TRI Global Research: https://www.tri.global/research/ todoist: <a href="https://todoist.com/" rel="nofollow" target="_blank">https://todoist.com/</a> Contrastive Learning of Structured World Models: <a href="https://arxiv.org/abs/2002.05709" rel="nofollow" target="_blank">https://arxiv.org/abs/2002.05709</a> SimCLR: <a href="https://arxiv.org/abs/2002.05709" rel="nofollow" target="_blank">https://arxiv.org/abs/2002.05709</a> --- Get our podcast on these platforms: Apple Podcasts: <a href="http://wandb.me/apple-podcasts​​" rel="nofollow" target="_blank">http://wandb.me/apple-podcasts​​</a> Spotify: <a href="http://wandb.me/spotify​" rel="nofollow" target="_blank">http://wandb.me/spotify​</a> Google Podcasts: <a href="http://wandb.me/google-podcasts​​" rel="nofollow" target="_blank">http://wandb.me/google-podcasts​​</a> YouTube: <a href="http://wandb.me/youtube​​" rel="nofollow" target="_blank">http://wandb.me/youtube​​</a> Soundcloud: <a href="http://wandb.me/soundcloud​" rel="nofollow" target="_blank">http://wandb.me/soundcloud​</a> Join our community of ML practitioners where we host AMAs, share interesting projects and meet other people working in Deep Learning: <a href="http://wandb.me/slack​​" rel="nofollow" target="_blank">http://wandb.me/slack​​</a> 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: <a href="https://wandb.ai/fully-connected" rel="nofollow" target="_blank">https://wandb.ai/fully-connected</a>

Adrien Gaidon — Advancing ML Research in Autonomous Vehicles

In this, the kickoff episode of AI Platforms Vol. 2, we're joined by Adrien Gaidon, Machine Learning Lead at Toyota Research Institute. Adrien and I caught up to discuss his team’s work on deploying distributed deep learning in the cloud, at scale. In our conversation, we discuss: • The beginning and gradual scaling up of TRI's platform.• Their distributed deep learning methods, including their use of stock Pytorch, and much more!

In this, the kickoff episode of AI Platforms Vol. 2, we're joined by Adrien Gaidon, Machine Learning Lead at Toyota Research Institute. Adrien and I caught up to discuss his team’s work on deploying distributed deep learning in the cloud, at scale. In our conversation, we discuss:  • The beginning and gradual scaling up of TRI's platform. • Their distributed deep learning methods, including their use of stock Pytorch, and much more!