Gradient Dissent: Conversations on AI

Latest Episodes:

Sean Taylor — Business Decision Problems May 13, 2021

Show notes

Sean joins us to chat about ML models and tools at Lyft Rideshare Labs, Python vs R, time series forecasting with Prophet, and election forecasting.

---

Sean Taylor is a Data Scientist at (and former Head of) Lyft Rideshare Labs, and specializes in methods for solving causal inference and business decision problems. Previously, he was a Research Scientist on Facebook's Core Data Science team. His interests include experiments, causal inference, statistics, machine learning, and economics.

Connect with Sean:

Personal website: https://seanjtaylor.com/

Twitter: https://twitter.com/seanjtaylor

LinkedIn: https://www.linkedin.com/in/seanjtaylor/

---

Topics Discussed:

0:00 Sneak peek, intro

0:50 Pricing algorithms at Lyft

07:46 Loss functions and ETAs at Lyft

12:59 Models and tools at Lyft

20:46 Python vs R

25:30 Forecasting time series data with Prophet

33:06 Election forecasting and prediction markets

40:55 Comparing and evaluating models

43:22 Bottlenecks in going from research to production

Transcript:

http://wandb.me/gd-sean-taylor

Links Discussed:

"How Lyft predicts a rider’s destination for better in-app experience"": https://eng.lyft.com/how-lyft-predicts-your-destination-with-attention-791146b0a439

Prophet: https://facebook.github.io/prophet/

Andrew Gelman's blog post "Facebook's Prophet uses Stan": https://statmodeling.stat.columbia.edu/2017/03/01/facebooks-prophet-uses-stan/

Twitter thread "Election forecasting using prediction markets": https://twitter.com/seanjtaylor/status/1270899371706466304

"An Updated Dynamic Bayesian Forecasting Model for the 2020 Election": https://hdsr.mitpress.mit.edu/pub/nw1dzd02/release/1

---

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

Polly Fordyce — Microfluidic Platforms and Machine Learning Apr 29, 2021

Show notes

Polly explains how microfluidics allow bioengineering researchers to create high throughput data, and shares her experiences with biology and machine learning.

---

Polly Fordyce is an Assistant Professor of Genetics and Bioengineering and fellow of the ChEM-H Institute at Stanford. She is the Principal Investigator of The Fordyce Lab, which focuses on developing and applying new microfluidic platforms for quantitative, high-throughput biophysics and biochemistry.

Twitter: https://twitter.com/fordycelab

Website: http://www.fordycelab.com/

---

Topics Discussed:

0:00 Sneak peek, intro

2:11 Background on protein sequencing

7:38 How changes to a protein's sequence alters its structure and function

11:07 Microfluidics and machine learning

19:25 Why protein folding is important

25:17 Collaborating with ML practitioners

31:46 Transfer learning and big data sets in biology

38:42 Where Polly hopes bioengineering research will go

42:43 Advice for students

Transcript:

http://wandb.me/gd-polly-fordyce

Links Discussed:

"The Weather Makers": https://en.wikipedia.org/wiki/The_Wea...

---

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

https://wandb.ai/fully-connected

Adrien Gaidon — Advancing ML Research in Autonomous Vehicles Apr 22, 2021

Show notes

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

https://wandb.ai/fully-connected

Nimrod Shabtay — Deployment and Monitoring at Nanit Apr 15, 2021

Show notes

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

Chris Mattmann — ML Applications on Earth, Mars, and Beyond Apr 08, 2021

Show notes

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

https://wandb.ai/fully-connected

Vladlen Koltun — The Power of Simulation and Abstraction Apr 01, 2021

Show notes

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

Dominik Moritz — Building Intuitive Data Visualization Tools Mar 25, 2021

Show notes

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

Cade Metz — The Stories Behind the Rise of AI Mar 18, 2021

Show notes

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

Dave Selinger — AI and the Next Generation of Security Systems Mar 11, 2021

Show notes

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

Tim & Heinrich — Democraticizing Reinforcement Learning Research Mar 04, 2021

Show notes

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

Our TOPPODCAST Picks

Follow Us

Stay Connected

Gradient Dissent: Conversations on AI

Related Podcasts

Links

Stay Connected