Chai Time Data Science

Latest Episodes:

Eugene Khvedchenya | Kaggle, Computer Vision & Best Code Practises | Severstal Steel, 4th Pos Sol Jan 09, 2020

Show notes

Personal Note: This interview and all future will have fixed subtitles for the non-native English speaking (also lazy) audience along with blog posts to be released at: sanyambhutani.com

Video Version available here: https://youtu.be/TwhJfZHx10s

Subscribe here to the newsletter: https://tinyletter.com/sanyambhutani

In this episode, Sanyam Bhutani interviews Eugene Khvedchenya: Kaggle Comp Master and Computer Vision Consultant.

They talk all about his journey into the field and Kaggle, and his recent team gold finish on the Severstal: Steel Defect Detection Kaggle competition, where his team finished fourth, bringing another gold medal to his profile.

Eugene also says many great pieces of advice around writing code, good code, and specially good code for Kaggle competitions, along with our discussion on his open source efforts on Albumentations and another framework that he's currently working on, called Pytorch toolbelt.

Links:

Severstal Steel Detection Comp: https://www.kaggle.com/c/severstal-steel-defect-detection/discussion/114716

AMA Thread: https://www.kaggle.com/c/severstal-steel-defect-detection/discussion/114291

Albumentations & Interview with Vladimir Iglovikov: https://youtu.be/JS9xol0VmA4

fast.ai course: https://course.fast.ai

Follow:

Eugene Khvedchenya: https://www.linkedin.com/in/cvtalks/?originalSubdomain=ua

https://medium.com/@eugenekhvedchenya

https://www.instagram.com/ekhvedchenya/?hl=en

https://www.kaggle.com/bloodaxe

Join: ods.ai

Sanyam Bhutani:

https://twitter.com/bhutanisanyam1

Blog: sanyambhutani.com

About: https://sanyambhutani.com/tag/chaitimedatascience/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani. You can expect weekly episodes every available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience Intro track: Flow by LiQWYD https://soundcloud.com/liqwyd

Interview with Arno Candel | AutoML | Physics | H2O.ai | CTDS.Show Dec 12, 2019

Show notes

Chai Time Data Science Playlist: https://www.youtube.com/playlist?list=PLLvvXm0q8zUbiNdoIazGzlENMXvZ9bd3x

Audio (Podcast Version) available here: https://anchor.fm/chaitimedatascience

Subscribe here to the newsletter: https://tinyletter.com/sanyambhutani

In this episode, Sanyam Bhutani interviews Dr. Arno Candel: CTO at H2O.ai

They talk about Arno’s journey into the field with amazing comments and insights by Arno applicable to the field.

They talk all about Arno’s journey and ML, Automated Machine Learning Broadly speaking. Arno’s journey from Physics to Software Engineering to Machine Learning Broadly speaking, his journey at H2O.

They also discuss H2O’s products, vision and The “Maker Culture”

Links:

Interview with SRK: https://sanyambhutani.com/interview-with-twice-kaggle-grandmaster-and-data-scientist-at-h2o-ai--sudalai-rajkumar/

Follow:

Arno Candel:

https://twitter.com/arnocandel

https://www.linkedin.com/in/candel/

H2O.AI:

https://twitter.com/h2oai

https://www.linkedin.com/company/h2oai

Sanyam Bhutani:

https://twitter.com/bhutanisanyam1

Blog: sanyambhutani.com

About:

http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every available as Video, Podcast, and blogposts.

Flow by LiQWYD https://soundcloud.com/liqwyd

Interview with Jeremy Howard | fast.ai | Kaggle | Machine Learning Research Dec 08, 2019

Show notes

Personal Note: I'm extremely excited and really honoured to share this interview!

Show notes: https://sanyambhutani.com/interview-with-jeremy-howard/

Audio (Podcast Version) available here: https://anchor.fm/chaitimedatascience

Subscribe here to the newsletter: https://tinyletter.com/sanyambhutani

In this episode, Sanyam Bhutani interviews Jeremy Howard: Co-Founder at fast.ai and Guru to the complete fast.ai community.

They talk all about Jeremy's journey into through the field as a Consultant to Founder to Kaggle Rank 1 followed by founding fast.ai.

They also discuss all about the fast.ai forums: The research that goes into it, how Jeremy and Sylvain collaborate on research and how the course is prepared.

Links:

fast.ai course: https://course.fast.ai

Interview with Sylvain Gugger:

Interview with Jason Antic (Creator of DeOldify):

Follow:

Jeremy Howard:

https://twitter.com/jeremyphoward

Fast.ai: https://twitter.com/fastdotai

https://fast.ai

Sanyam Bhutani:

https://twitter.com/bhutanisanyam1

Blog: sanyambhutani.com

About: http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani. You can expect weekly episodes every available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience Intro track: Flow by LiQWYD https://soundcloud.com/liqwyd

DistilBERT | Research at Hugging Face | NLP and Open Source | Interview with Victor Sanh Dec 05, 2019

Show notes

Audio (Podcast Version) available here: https://anchor.fm/chaitimedatascience

Subscribe here to the newsletter: https://tinyletter.com/sanyambhutani

In this episode, Sanyam Bhutani interviews the Victor Sanh, Research Scientist at Hugging Face. In this interview, they talk all about his journey into the field of NLP and Machine Learning.

They also talk about Research in general and Research at Hugging Face along with a discussion on DistilBERT.

Links:

DistilBERT: https://medium.com/huggingface/distilbert-8cf3380435b5

https://arxiv.org/abs/1910.01108

Transformers Repo:

https://github.com/huggingface/transformers

https://medium.com/huggingface/distilbert-8cf3380435b5

Follow:

Victor Sanh:

https://twitter.com/sanhestpasmoi?lang=en

https://www.linkedin.com/in/victor-sanh/?locale=en_US

Hugging Face:

https://twitter.com/huggingface

https://huggingface.co/

https://medium.com/huggingface

Sanyam Bhutani:

https://twitter.com/bhutanisanyam1

Blog: sanyambhutani.com

About:

http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Intro track: Flow by LiQWYD https://soundcloud.com/liqwyd

Kaggle Discussions Rank #1, x2 Grandmaster: Dr. Jean Francois Puget | IEEE-CIS Comp 2nd Pos Sol Nov 21, 2019

Show notes

Audio Version available here: https://anchor.fm/chaitimedatascience

Newsletter: https://tinyletter.com/sanyambhutani

https://hackernoon.com/interview-with-twice-kaggle-grandmaster-dr-jean-francois-puget-cpmp-6d92328e433a

In this Episode, Sanyam Bhutani interviews x2 Kaggle GrandMaster, King of Kaggle Discussions: Dr. Jean Francois Puget, Ranked #1 in Discussions Tier.

In this interview they talk all about IEEE-CIS Fraud Detection Kaggle Competition, CPMP's approach to Kaggle in general and also very specifically to this competition.

They also dig deeper into a few topics that pick up right after the previous interview.

Comp Link: https://www.kaggle.com/c/ieee-fraud-detection

Solution Overview: https://www.kaggle.com/c/ieee-fraud-detection/discussion/111321#latest-648250

Interview with Machine Learning Hero Series: https://hackernoon.com/interview-with-machine-learning-heroes-0ifi3yyg

Follow:

Dr. Jean Francois Puget

https://twitter.com/jfpuget

https://www.linkedin.com/in/jfpuget/

https://www.kaggle.com/cpmpml

Sanyam Bhutani:

https://twitter.com/bhutanisanyam1

About:

http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Intro track:

Flow by LiQWYD https://soundcloud.com/liqwyd

Medalling in all Entered Kaggle Comp | IEEE-CIS Comp 6th Pos Sol | Interview with Dr Philipp Singer Nov 04, 2019

Show notes

Video Version available here: https://youtu.be/7sh5QrUIAHI

Newsletter: https://tinyletter.com/sanyambhutani

In this Episode, Sanyam Bhutani interviews Dr. Philipp Singer, Sr. Data Scientist at UNIQA Insurance Group and Kaggle 2x Master, Currently in Top 30 of competitions tier and Top 10 in the Discussions Tier.

They talk all about his journey into the field, along with his approach to Kaggling where he medals in every single competition that he participates in, with 83% Gold medals and 17% Silver medals (5, 1 respectively)!!!

They also discuss "The Zoo" (Team)'s recent 6th position Gold Medal finish on the IEEE-CIS Fraud Detection Kaggle Competition.

Comp Link: https://www.kaggle.com/c/ieee-fraud-detection

Solution Overview: https://www.kaggle.com/c/ieee-fraud-detection/discussion/111247

Interview with Machine Learning Hero Series: https://hackernoon.com/interview-with-machine-learning-heroes-0ifi3yyg

Follow:

Philipp Singer

https://twitter.com/ph_singer

https://www.philippsinger.info/

Sanyam Bhutani: https://twitter.com/bhutanisanyam1

About:

http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every Sunday, Thursday available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Intro track:

Flow by LiQWYD https://soundcloud.com/liqwyd

Predicting Molecular Prop Kaggle Comp 2nd Place Sol | Interview with Kaggle Master Andres Torrubia Nov 01, 2019

Show notes

Video Version available here: https://youtu.be/sqo2h7aYPPk

Newsletter: https://tinyletter.com/sanyambhutani

In this Episode, Sanyam Bhutani interviews Andres Torrubia, CEO of Fixr.com and Kaggle Competition Master. They talk all about his journey into the field, along with the predicting molecular property challenge along with Andres' Bruce Wayne during the day and Batman of Kaggle during the night lifestyle.

Predicting Molecular Prop Comp: https://www.kaggle.com/c/champs-scalar-coupling

Solution Overview + Source Code by Andres: https://www.kaggle.com/c/champs-scalar-coupling/discussion/108845#latest-662721

Interview with Machine Learning Hero Series: https://medium.com/dsnet/interviews-with-machine-learning-heroes-ad9358385278

Follow:

Andres Torrubia:

https://twitter.com/antor

Sanyam Bhutani: https://twitter.com/bhutanisanyam1

About:

http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every Sunday, Thursday available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Intro track:

Flow by LiQWYD https://soundcloud.com/liqwyd

DeepMind & AlphaGo | Deep Learning Research | Swift For Tensorflow | Interview with Dr. Marc Lanctot Oct 27, 2019

Show notes

Newsletter: https://tinyletter.com/sanyambhutani

Personal Note: I'm really honored to share this conversation. I really hope you enjoy listening to it as much as I enjoyed talking to Dr. Marc Lanctot.

In this Episode, Sanyam Bhutani interviews Dr. Marc Lactot, a Research Scientist at DeepMind. In this interview, they talk all about Research at DeepMind, Deep Learning Research, AlphaGo. They also talk all about Swift For Tensorflow and OpenSpiel.

Dr. Marc Lanctot is a research scientist at Google DeepMind. Previously, he was a post-doctoral researcher at the Maastricht University Games and AI Group, working with Mark Winands. During his PhD, Marc worked on sampling algorithms for equilibrium computation and decision-making in games. His research interests include in general multiagent learning (and planning), computational game theory, reinforcement learning, and game-tree search.

Open Spiel: https://deepmind.com/research/open-source/openspiel

Interview with Machine Learning Hero Series: https://medium.com/dsnet/interviews-with-machine-learning-heroes-ad9358385278

Links from the podcast:

- Commodore 64: https://en.wikipedia.org/wiki/Commodore_64

- Intellivision (early console!): https://en.wikipedia.org/wiki/Intellivision

- AD&D Treasure of Tarmin (Intellivision game with 3D perspective-- pretty advanced for its time!): https://en.wikipedia.org/wiki/Advanced_Dungeons_%26_Dragons:_Treasure_of_Tarmin

- Montezuma's revenge: https://en.wikipedia.org/wiki/Montezuma%27s_Revenge_(video_game)

Follow:

Dr. Marc Lanctot

https://twitter.com/sharky6000

http://mlanctot.info/

https://www.linkedin.com/in/marc-lanctot-a1619095/?originalSubdomain=ca

Sanyam Bhutani: https://twitter.com/bhutanisanyam1

About:

http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every Sunday, Thursday available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Swift For Tensorflow | Software Engineering Internship at Google | Interview with Bart Chrazaszcz Oct 27, 2019

Show notes

Audio Version available here: https://anchor.fm/chaitimedatascience

Newsletter: https://tinyletter.com/sanyambhutani

In this Episode, Sanyam Bhutani interviews Bart Chrzaszcz, an undergraduate at the University of Waterloo. They talk about Bart's Google Software Engineering Internship where he contributed to Swift For Tensorflow, OpenSpiel.

Interview with Machine Learning Hero Series: https://medium.com/dsnet/interviews-with-machine-learning-heroes-ad9358385278

Follow:

Bart:

https://twitter.com/bart_chr

Sanyam Bhutani: https://twitter.com/bhutanisanyam1

About:

http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every Sunday, Thursday available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Boris Dorado Interview | Gold Medalling in First Kaggle Comp | Predicting Molecular Prop Kaggle Comp Solution Oct 21, 2019

Show notes

Audio Version available here: https://anchor.fm/chaitimedatascience

Newsletter: https://tinyletter.com/sanyambhutani

In this Episode, Sanyam Bhutani interviews Dr. Boris Dorado. They talk about Boris's first Kaggle Competition experience and his takeaways from teaming up with 4 Kaggle Grandmasters in the "Predicting Molecular Property Kaggle Competition" and their team's solution.

AMA Thread: https://www.kaggle.com/c/champs-scalar-coupling/discussion/109670

Interview with Machine Learning Hero Series: https://medium.com/dsnet/interviews-with-machine-learning-heroes-ad9358385278

Follow:

Dr. Boris Dorado:

https://www.linkedin.com/in/boris-dorado/

https://borisdorado.com/

Sanyam Bhutani: https://twitter.com/bhutanisanyam1

About:

http://chaitimedatascience.com/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every Sunday, Thursday available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Our TOPPODCAST Picks

Follow Us

Stay Connected

Related Podcasts

Links

Stay Connected