Himalaya-The Podcast Player

4.8K Ratings
Open In App
title

Machine Learning Cafe

Miklos Zoltan Toth

0
Followers
0
Plays
Machine Learning Cafe

Machine Learning Cafe

Miklos Zoltan Toth

0
Followers
0
Plays
OVERVIEWEPISODESYOU MAY ALSO LIKE

Details

About Us

This is a machine-learning-focused Podcast, where we interview people in the field of Artificial Intelligence and discuss interesting technical topics of Machine Learning. In the episodes, we focus on business-related use-cases (especially with Deep Learning ) and we also try to bring some technical white papers to the ground, not forgetting on the way that there are always some people behind the technology, so we try to understand their motivation and drive.

Latest Episodes

"Monkeys with laptops" - the (hi)story of applying AI in real life with Denis Rothman - 014

In this "extra" episode, our guest is Denis Rothman, who is an Artificial Intelligence Specialist. He has spent 40 years in this industry, he is the author of the book called "Artificial Intelligence by Example". He is a teacher, a speaker, and an exceptional expert. He has a very special view on what software development is and how to build-up systems that may or may not use artificial intelligence. We believe he is one of the brightest minds we have ever talked to.

74 MIN2 w ago
Comments
"Monkeys with laptops" - the (hi)story of applying AI in real life with Denis Rothman - 014

Conversational AI at Rasa with Vladimir Vlasov - 013

In this episode, our guest is Vladimir Vlasov, a senior ML researcher at Rasa. If you don't know Rasa, it's a company that is building a standard infrastructure for conversational AI. Vladimir works on Rasa's ML-based dialogue tools which allow developers to automate contextual conversations. So we were talking about state-of-the-art area of conversational AI and NLP, also briefly how Rasa’s framework is built up, and what are the technical problems to be solved, and the future of conversational AI.

63 MINJUN 10
Comments
Conversational AI at Rasa with Vladimir Vlasov - 013

What's real and what's hype? - Decades of ML with Eugene Dubossarsky - 012

In this episode, our guest is Eugene Dubossarsky, who is the chief data scientist at AlphaZetta and co-founder at multiple data science companies in Australia. Eugene is dealing with machine learning since the 80s, so he has a very strong opinion about different topics in this industry. We talked about random forests, neural nets, boosting strategies, the importance of understanding data and statistics, and about the effects of the current and upcoming crisis either.

52 MINMAY 21
Comments
What's real and what's hype? - Decades of ML with Eugene Dubossarsky - 012

Extra: Machine Learning at John Deere with Marco Lemessi - 011

We recorded an extra and special episode, our guest is Marco Lemessi, who is a ML leader at John Deere. He will share some of the business aspects and also problems of the ML projects they are facing at one of the biggest agricultural companies in the world. He has a very broad perspective about business cases and data science and optimization problems. He will talk about precision agriculture, problems of labeling on large dataset, legal aspects of AI.

47 MINMAY 12
Comments
Extra: Machine Learning at John Deere with Marco Lemessi - 011

The World’s first Quadruple Kaggle Grandmaster - Abhishek Thakur - 010

In this episode our guest is Abhishek Thakur, who is the Chief Data Scientist at Boost.ai in Norway. Abhishek has become the World’s first Quadruple Grandmaster on Kaggle. So we asked him about his experiences of the 150 competitions he has taken part in. So, what are the tricks here? How can someone participate in so many competitions, rank high and have a work besides these? Although he has been so successful you will see that he is a very humble person.

44 MINMAY 6
Comments
The World’s first Quadruple Kaggle Grandmaster - Abhishek Thakur - 010

Everything is just a wicked graph with Benedek Rozemberczki - 009

Our guest is Benedek Rozemberczki who is a Data Science Phd candidate at University of Edinburgh and owner of the github repo Karate Club where he implemented more than 30 scientific papers about Graphs and ML. More information: https://bit.ly/3awla0U Website of the podcast: http://machinelearningcafe.org/ Host's LinkedIn: https://www.linkedin.com/in/miklostoth/ Co-Host LinkedIn: https://www.linkedin.com/in/levente-szabados-76334728/ Write an email to the host: miklos@machinelearningcafe.org

50 MINAPR 22
Comments
Everything is just a wicked graph with Benedek Rozemberczki - 009

Ratings and Marketing Attribution at Foursquare with Max Sklar - 008

In this episode our guest is Max Sklar who works as Engineering and Innovation Labs advisor at Foursquare. We talked about ratings and the problems about deciding if a rating is positive or negative, and the problems about different languages. In the second part of the show we talked about marketing attribution and causality. More info: http://bit.ly/2wyDWXp

56 MINMAR 5
Comments
Ratings and Marketing Attribution at Foursquare with Max Sklar - 008

MISH Activation Function with Diganta Misra - 007

In this episode, out guest is Diganta Misra, who is the founder of Landskape AI, which is a research lab aimed at solving the most challenging questions of Deep Learning. Diganta is a Mathematician who invented the activation function called MISH, which beats Google's activation function called Swish in most computer vision tasks. He released his paper last summer and the project got already 600 stars on Github. More info: http://bit.ly/2UnSuTp

50 MINFEB 3
Comments
MISH Activation Function with Diganta Misra - 007

Finding the label errors with Cleanlab with Curtis Northcutt - 006

EIn this episode, I talked with Curtis Northcutt about his application Cleanlab, with which you can find label errors in your dataset. Cleanlab computes cross-validated probabilities, the confident joint, and the statistics used in uncertainty estimation for dataset labels, and it ranks and sorts the labels by the probabilities of error, so you can easily find them in your dataset. Show notes: http://podcast.machinelearningcafe.org/finding-the-label-errors-with-cleanlab-with-curtis-northcutt-006

55 MINJAN 23
Comments
Finding the label errors with Cleanlab with Curtis Northcutt - 006

A New Deep Learning Optimizer called Ranger with Less Wright - 005

In this episode, we interview Less Wright, who has set 13 records on the fast.ai leaderboard, and we talk about one of his tricks is using cutting-edge optimizers, he also developed one, which is called Ranger. He talks also about different strategies of using Deep Learning optimizers, it is worth to take those into consideration. We also tested Ranger and in our case, it also outperformed Adam/RAdam variants. Co-host is Levente Szabados.

36 MINJAN 8
Comments
A New Deep Learning Optimizer called Ranger with Less Wright - 005

Latest Episodes

"Monkeys with laptops" - the (hi)story of applying AI in real life with Denis Rothman - 014

In this "extra" episode, our guest is Denis Rothman, who is an Artificial Intelligence Specialist. He has spent 40 years in this industry, he is the author of the book called "Artificial Intelligence by Example". He is a teacher, a speaker, and an exceptional expert. He has a very special view on what software development is and how to build-up systems that may or may not use artificial intelligence. We believe he is one of the brightest minds we have ever talked to.

74 MIN2 w ago
Comments
"Monkeys with laptops" - the (hi)story of applying AI in real life with Denis Rothman - 014

Conversational AI at Rasa with Vladimir Vlasov - 013

In this episode, our guest is Vladimir Vlasov, a senior ML researcher at Rasa. If you don't know Rasa, it's a company that is building a standard infrastructure for conversational AI. Vladimir works on Rasa's ML-based dialogue tools which allow developers to automate contextual conversations. So we were talking about state-of-the-art area of conversational AI and NLP, also briefly how Rasa’s framework is built up, and what are the technical problems to be solved, and the future of conversational AI.

63 MINJUN 10
Comments
Conversational AI at Rasa with Vladimir Vlasov - 013

What's real and what's hype? - Decades of ML with Eugene Dubossarsky - 012

In this episode, our guest is Eugene Dubossarsky, who is the chief data scientist at AlphaZetta and co-founder at multiple data science companies in Australia. Eugene is dealing with machine learning since the 80s, so he has a very strong opinion about different topics in this industry. We talked about random forests, neural nets, boosting strategies, the importance of understanding data and statistics, and about the effects of the current and upcoming crisis either.

52 MINMAY 21
Comments
What's real and what's hype? - Decades of ML with Eugene Dubossarsky - 012

Extra: Machine Learning at John Deere with Marco Lemessi - 011

We recorded an extra and special episode, our guest is Marco Lemessi, who is a ML leader at John Deere. He will share some of the business aspects and also problems of the ML projects they are facing at one of the biggest agricultural companies in the world. He has a very broad perspective about business cases and data science and optimization problems. He will talk about precision agriculture, problems of labeling on large dataset, legal aspects of AI.

47 MINMAY 12
Comments
Extra: Machine Learning at John Deere with Marco Lemessi - 011

The World’s first Quadruple Kaggle Grandmaster - Abhishek Thakur - 010

In this episode our guest is Abhishek Thakur, who is the Chief Data Scientist at Boost.ai in Norway. Abhishek has become the World’s first Quadruple Grandmaster on Kaggle. So we asked him about his experiences of the 150 competitions he has taken part in. So, what are the tricks here? How can someone participate in so many competitions, rank high and have a work besides these? Although he has been so successful you will see that he is a very humble person.

44 MINMAY 6
Comments
The World’s first Quadruple Kaggle Grandmaster - Abhishek Thakur - 010

Everything is just a wicked graph with Benedek Rozemberczki - 009

Our guest is Benedek Rozemberczki who is a Data Science Phd candidate at University of Edinburgh and owner of the github repo Karate Club where he implemented more than 30 scientific papers about Graphs and ML. More information: https://bit.ly/3awla0U Website of the podcast: http://machinelearningcafe.org/ Host's LinkedIn: https://www.linkedin.com/in/miklostoth/ Co-Host LinkedIn: https://www.linkedin.com/in/levente-szabados-76334728/ Write an email to the host: miklos@machinelearningcafe.org

50 MINAPR 22
Comments
Everything is just a wicked graph with Benedek Rozemberczki - 009

Ratings and Marketing Attribution at Foursquare with Max Sklar - 008

In this episode our guest is Max Sklar who works as Engineering and Innovation Labs advisor at Foursquare. We talked about ratings and the problems about deciding if a rating is positive or negative, and the problems about different languages. In the second part of the show we talked about marketing attribution and causality. More info: http://bit.ly/2wyDWXp

56 MINMAR 5
Comments
Ratings and Marketing Attribution at Foursquare with Max Sklar - 008

MISH Activation Function with Diganta Misra - 007

In this episode, out guest is Diganta Misra, who is the founder of Landskape AI, which is a research lab aimed at solving the most challenging questions of Deep Learning. Diganta is a Mathematician who invented the activation function called MISH, which beats Google's activation function called Swish in most computer vision tasks. He released his paper last summer and the project got already 600 stars on Github. More info: http://bit.ly/2UnSuTp

50 MINFEB 3
Comments
MISH Activation Function with Diganta Misra - 007

Finding the label errors with Cleanlab with Curtis Northcutt - 006

EIn this episode, I talked with Curtis Northcutt about his application Cleanlab, with which you can find label errors in your dataset. Cleanlab computes cross-validated probabilities, the confident joint, and the statistics used in uncertainty estimation for dataset labels, and it ranks and sorts the labels by the probabilities of error, so you can easily find them in your dataset. Show notes: http://podcast.machinelearningcafe.org/finding-the-label-errors-with-cleanlab-with-curtis-northcutt-006

55 MINJAN 23
Comments
Finding the label errors with Cleanlab with Curtis Northcutt - 006

A New Deep Learning Optimizer called Ranger with Less Wright - 005

In this episode, we interview Less Wright, who has set 13 records on the fast.ai leaderboard, and we talk about one of his tricks is using cutting-edge optimizers, he also developed one, which is called Ranger. He talks also about different strategies of using Deep Learning optimizers, it is worth to take those into consideration. We also tested Ranger and in our case, it also outperformed Adam/RAdam variants. Co-host is Levente Szabados.

36 MINJAN 8
Comments
A New Deep Learning Optimizer called Ranger with Less Wright - 005
hmly
Welcome to Himalaya LearningDozens of podcourses featuring over 100 experts are waiting for you.