Gradient Dissent: Conversations on AI

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/adnothing LinkedIn: https://www.linkedin.com/in/adrien-gaidon-63ab2358/ Personal website: https://adriengaidon.com/ --- 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: http://wandb.me/gd-adrien-gaidon Links Discussed: TRI Global Research: https://www.tri.global/research/ todoist: https://todoist.com/ Contrastive Learning of Structured World Models: https://arxiv.org/abs/2002.05709 SimCLR: 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

22 Apr 202148min

A look at how Nimrod and the team at Nanit are building smart baby monitor systems, from data collection to model deployment and production monitoring. --- Nimrod Shabtay is a Senior Computer Vision Algorithm Developer at Nanit, a New York-based company that's developing better baby monitoring devices. Connect with Nimrod: LinkedIn: https://www.linkedin.com/in/nimrod-shabtay-76072840/ --- Links Discussed: Guidelines for building an accurate and robust ML/DL model in production: https://engineering.nanit.com/guideli...​ Careers at Nanit: https://www.nanit.com/jobs​ --- Get our podcast on these platforms: Apple Podcasts: http://wandb.me/apple-podcasts​​ Spotify: http://wandb.me/spotify​ Google: 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 more: http://wandb.me/slack​​ Our gallery features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, and industry leaders sharing best practices: https://wandb.ai/gallery

15 Apr 202133min

Chris shares some of the incredible work and innovations behind deep space exploration at NASA JPL and reflects on the past, present, and future of machine learning. --- Chris Mattmann is the Chief Technology and Innovation Officer at NASA Jet Propulsion Laboratory, where he focuses on organizational innovation through technology. He's worked on space missions such as the Orbiting Carbon Observatory 2 and Soil Moisture Active Passive satellites. Chris is also a co-creator of Apache Tika, a content detection and analysis framework that was one of the key technologies used to uncover the Panama Papers, and is the author of "Machine Learning with TensorFlow, Second Edition" and "Tika in Action". Connect with Chris: Personal website: https://www.mattmann.ai/ Twitter: https://twitter.com/chrismattmann --- Topics Discussed: 0:00 Sneak peek, intro 0:52 On Perseverance and Ingenuity 8:40 Machine learning applications at NASA JPL 11:51 Innovation in scientific instruments and data formats 18:26 Data processing levels: Level 1 vs Level 2 vs Level 3 22:20 Competitive data processing 27:38 Kerbal Space Program 30:19 The ideas behind "Machine Learning with Tensorflow, Second Edition" 35:37 The future of MLOps and AutoML 38:51 Machine learning at the edge Transcript: http://wandb.me/gd-chris-mattmann Links Discussed: Perseverance and Ingenuity: https://mars.nasa.gov/mars2020/ Data processing levels at NASA: https://earthdata.nasa.gov/collaborate/open-data-services-and-software/data-information-policy/data-levels OCO-2: https://www.jpl.nasa.gov/missions/orbiting-carbon-observatory-2-oco-2 "Machine Learning with TensorFlow, Second Edition" (2020): https://www.manning.com/books/machine-learning-with-tensorflow-second-edition "Tika in Action" (2011): https://www.manning.com/books/tika-in-action Transcript: http://wandb.me/gd-chris-mattmann --- 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

8 Apr 202142min

From legged locomotion to autonomous driving, Vladlen explains how simulation and abstraction help us understand embodied intelligence. --- Vladlen Koltun is the Chief Scientist for Intelligent Systems at Intel, where he leads an international lab of researchers working in machine learning, robotics, computer vision, computational science, and related areas. Connect with Vladlen: Personal website: http://vladlen.info/ LinkedIn: https://www.linkedin.com/in/vladlenkoltun/ --- 0:00 Sneak peek and intro 1:20 "Intelligent Systems" vs "AI" 3:02 Legged locomotion 9:26 The power of simulation 14:32 Privileged learning 18:19 Drone acrobatics 20:19 Using abstraction to transfer simulations to reality 25:35 Sample Factory for reinforcement learning 34:30 What inspired CARLA and what keeps it going 41:43 The challenges of and for robotics Links Discussed Learning quadrupedal locomotion over challenging terrain (Lee et al., 2020): https://robotics.sciencemag.org/content/5/47/eabc5986.abstract Deep Drone Acrobatics (Kaufmann et al., 2020): https://arxiv.org/abs/2006.05768 Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning (Petrenko et al., 2020): https://arxiv.org/abs/2006.11751 CARLA: https://carla.org/ --- Check out the transcription and discover more awesome ML projects: http://wandb.me/vladlen-koltun​-podcast Get our podcast on these platforms: Apple Podcasts: http://wandb.me/apple-podcasts​​ Spotify: http://wandb.me/spotify​ Google: 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​​ Our gallery features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, and industry leaders sharing best practices: https://wandb.ai/gallery

1 Apr 202149min

Dominik shares the story and principles behind Vega and Vega-Lite, and explains how visualization and machine learning help each other. --- Dominik is a co-author of Vega-Lite, a high-level visualization grammar for building interactive plots. He's also a professor at the Human-Computer Interaction Institute Institute at Carnegie Mellon University and an ML researcher at Apple. Connect with Dominik Twitter: https://twitter.com/domoritz GitHub: https://github.com/domoritz Personal website: https://www.domoritz.de/ --- 0:00 Sneak peek, intro 1:15 What is Vega-Lite? 5:39 The grammar of graphics 9:00 Using visualizations creatively 11:36 Vega vs Vega-Lite 16:03 ggplot2 and machine learning 18:39 Voyager and the challenges of scale 24:54 Model explainability and visualizations 31:24 Underrated topics: constraints and visualization theory 34:38 The challenge of metrics in deployment 36:54 In between aggregate statistics and individual examples Links Discussed Vega-Lite: https://vega.github.io/vega-lite/ Data analysis and statistics: an expository overview (Tukey and Wilk, 1966): https://dl.acm.org/doi/10.1145/1464291.1464366 Slope chart / slope graph: https://vega.github.io/vega-lite/examples/line_slope.html Voyager: https://github.com/vega/voyager Draco: https://github.com/uwdata/draco Check out the transcription and discover more awesome ML projects: http://wandb.me/gd-domink-moritz --- Get our podcast on these platforms: Apple Podcasts: http://wandb.me/apple-podcasts​ Spotify: http://wandb.me/spotify​ Google: http://wandb.me/google-podcasts​ YouTube: http://wandb.me/youtube​ Soundcloud: http://wandb.me/soundcloud --- Join our community of ML practitioners where we host AMA's, share interesting projects and meet other people working in Deep Learning: http://wandb.me/slack​ Our gallery features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, and industry leaders sharing best practices: https://wandb.ai/gallery

25 Mar 202139min

How Cade got access to the stories behind some of the biggest advancements in AI, and the dynamic playing out between leaders at companies like Google, Microsoft, and Facebook. Cade Metz is a New York Times reporter covering artificial intelligence, driverless cars, robotics, virtual reality, and other emerging areas. Previously, he was a senior staff writer with Wired magazine and the U.S. editor of The Register, one of Britain’s leading science and technology news sites. His first book, "Genius Makers", tells the stories of the pioneers behind AI. Get the book: http://bit.ly/GeniusMakers Follow Cade on Twitter: https://twitter.com/CadeMetz/ And on Linkedin: https://www.linkedin.com/in/cademetz/ Topics discussed: 0:00 sneak peek, intro 3:25 audience and charachters 7:18 *spoiler alert* AGI 11:01 book ends, but story goes on 17:31 overinflated claims in AI 23:12 Deep Mind, OpenAI, building AGI 29:02 neuroscience and psychology, outsiders 34:35 Early adopters of ML 38:34 WojNet, where is credit due? 42:45 press covering AI 46:38 Aligning technology and need Read the transcript and discover awesome ML projects: http://wandb.me/cade-metz Get our podcast on these platforms: Apple Podcasts: http://wandb.me/apple-podcasts Spotify: http://wandb.me/spotify Google: http://wandb.me/google-podcasts YouTube: http://wandb.me/youtube Soundcloud: http://wandb.me/soundcloud Tune in to our bi-weekly virtual salon and listen to industry leaders and researchers in machine learning share their research: http://wandb.me/salon Join our community of ML practitioners where we host AMA's, share interesting projects and meet other people working in Deep Learning: http://wandb.me/slack Our gallery features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, and industry leaders sharing best practices: https://wandb.ai/gallery

18 Mar 202149min

Learn why traditional home security systems tend to fail and how Dave’s love of tinkering and deep learning are helping him and the team at Deep Sentinel avoid those same pitfalls. He also discusses the importance of combatting racial bias by designing race-agnostic systems and what their approach is to solving that problem. Dave Selinger is the co-founder and CEO of Deep Sentinel, an intelligent crime prediction and prevention system that stops crime before it happens using deep learning vision techniques. Prior to founding Deep Sentinel, Dave co-founded RichRelevance, an AI recommendation company. https://www.deepsentinel.com/ https://www.meetup.com/East-Bay-Tri-Valley-Machine-Learning-Meetup/ https://twitter.com/daveselinger Topics covered: 0:00 Sneak peek, smart vs dumb cameras, intro 0:59 What is Deep Sentinel, how does it work? 6:00 Hardware, edge devices 10:40 OpenCV Fork, tinkering 16:18 ML Meetup, Climbing the AI research ladder 20:36 Challenge of Safety critical applications 27:03 New models, re-training, exhibitionists and voyeurs 31:17 How do you prove your cameras are better? 34:24 Angel investing in AI companies 38:00 Social responsibility with data 43:33 Combatting bias with data systems 52:22 Biggest bottlenecks production Get our podcast on these platforms: Apple Podcasts: http://wandb.me/apple-podcasts Spotify: http://wandb.me/spotify Google: http://wandb.me/google-podcasts YouTube: http://wandb.me/youtube Soundcloud: http://wandb.me/soundcloud Read the transcript and discover more awesome machine learning material here: http://wandb.me/Dave-selinger-podcast Tune in to our bi-weekly virtual salon and listen to industry leaders and researchers in machine learning share their research: http://wandb.me/salon Join our community of ML practitioners where we host AMA's, share interesting projects and meet other people working in Deep Learning: http://wandb.me/slack Our gallery features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, and industry leaders sharing best practices: https://wandb.ai/gallery

11 Mar 202156min

Since reinforcement learning requires hefty compute resources, it can be tough to keep up without a serious budget of your own. Find out how the team at Facebook AI Research (FAIR) is looking to increase access and level the playing field with the help of NetHack, an archaic rogue-like video game from the late 80s. Links discussed: The NetHack Learning Environment: https://ai.facebook.com/blog/nethack-learning-environment-to-advance-deep-reinforcement-learning/ Reinforcement learning, intrinsic motivation: https://arxiv.org/abs/2002.12292 Knowledge transfer: https://arxiv.org/abs/1910.08210 Tim Rocktäschel is a Research Scientist at Facebook AI Research (FAIR) London and a Lecturer in the Department of Computer Science at University College London (UCL). At UCL, he is a member of the UCL Centre for Artificial Intelligence and the UCL Natural Language Processing group. Prior to that, he was a Postdoctoral Researcher in the Whiteson Research Lab, a Stipendiary Lecturer in Computer Science at Hertford College, and a Junior Research Fellow in Computer Science at Jesus College, at the University of Oxford. https://twitter.com/_rockt Heinrich Kuttler is an AI and machine learning researcher at Facebook AI Research (FAIR) and before that was a research engineer and team lead at DeepMind. https://twitter.com/HeinrichKuttler https://www.linkedin.com/in/heinrich-kuttler/ Topics covered: 0:00 a lack of reproducibility in RL 1:05 What is NetHack and how did the idea come to be? 5:46 RL in Go vs NetHack 11:04 performance of vanilla agents, what do you optimize for 18:36 transferring domain knowledge, source diving 22:27 human vs machines intrinsic learning 28:19 ICLR paper - exploration and RL strategies 35:48 the future of reinforcement learning 43:18 going from supervised to reinforcement learning 45:07 reproducibility in RL 50:05 most underrated aspect of ML, biggest challenges? Get our podcast on these other platforms: Apple Podcasts: http://wandb.me/apple-podcasts Spotify: http://wandb.me/spotify Google: http://wandb.me/google-podcasts YouTube: http://wandb.me/youtube Soundcloud: http://wandb.me/soundcloud Tune in to our bi-weekly virtual salon and listen to industry leaders and researchers in machine learning share their research: http://wandb.me/salon Join our community of ML practitioners where we host AMA's, share interesting projects and meet other people working in Deep Learning: http://wandb.me/slack Our gallery features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, and industry leaders sharing best practices: https://wandb.ai/gallery

4 Mar 202154min