Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Vanilla deep learning is so 2010s. Did you start learning about categorical deep learning yet?! 🔥 with Bruno Gavranović @bgavran3 and Paul Lessard paul lessard and Tim Scarfe

Machine Learning Street Talk

38,712 subscribers

23,825 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

3 Comments

Machine Learning Street Talk2 years ago

More info:

Charles Wang2 years ago

@bgavran3 @paullessard @ecsquendor If the goal is for AI, one should explore ideas along the lines of this paper “Constructor Theory as Process Theory” by @StefanoGogioso, @vinnylarouge, Carlo Maria Scandolo, @coecke, @quantum_physics

🌊2 years ago

@PetarV_93 @bgavran3 @paullessard @ecsquendor 🙄 constructs and topos

Related Videos

What is learning? Paul A. Kirschner and I discuss why learning is inextricably linked with memory.

What is learning? Paul A. Kirschner and I discuss why learning is inextricably linked with memory.

Carl Hendrick

18,483 views • 1 year ago

I flipped through 300 pages of deep learning math puzzles by hand ✍️ This is the proof copy of the "Deep Learning Math Workbook" I made to help you learn and practice 12 foundational math concepts below👇

I flipped through 300 pages of deep learning math puzzles by hand ✍️ This is the proof copy of the "Deep Learning Math Workbook" I made to help you learn and practice 12 foundational math concepts below👇

Tom Yeh

2,378,310 views • 1 year ago

"Increasing access and transforming teaching and learning is about smaller learning environments with unbundled assets." Amy McGrath discusses the future of teaching and learning at the 2023 The Yass Prize Semifinalist Showcase. #YassPrize

"Increasing access and transforming teaching and learning is about smaller learning environments with unbundled assets." Amy McGrath discusses the future of teaching and learning at the 2023 The Yass Prize Semifinalist Showcase. #YassPrize

Forbes

20,980 views • 2 years ago

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning investigated the application of Deep Reinforcement Learning (Deep RL) for low-cost, miniature humanoid hardware in a dynamic environment, showing the method can synthesize sophisticated and safe movement skills making up complex behavioral strategies in a simplified one-versus-one (1v1) soccer game abs: project page:

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning investigated the application of Deep Reinforcement Learning (Deep RL) for low-cost, miniature humanoid hardware in a dynamic environment, showing the method can synthesize sophisticated and safe movement skills making up complex behavioral strategies in a simplified one-versus-one (1v1) soccer game abs: project page:

AK

293,352 views • 3 years ago

Deep learning works extraordinarily well. And we still largely don't know why. A new paper from Jamie Simon, Daniel Kunin, and 12 co-authors argues that a scientific theory of deep learning is emerging, and coins a name for the emerging field: learning mechanics. We sat down with Jamie and Dan on Generally Intelligent to talk about what a physics of deep learning would actually look like, why now, and what's left to figure out. 3:05 Learning mechanics as the physics to mechanistic interpretability's biology 4:13 Why deep learning needs a theory 7:07 Why deep learning is uniquely hard to engineer 12:11 How a week in the woods became a paper 25:59 The barrier to theory isn't opacity, but complexity 36:26 Deep learning's first gas law 47:22 Why more particles makes the problem easier 56:22 The discretization hypothesis 1:01:50 The strongest signal that a compact theory exists 1:05:07 The Platonic Representation Hypothesis 1:15:41 Why learning mechanics and mech interp need each other 1:25:29 Theory as safety infrastructure

Deep learning works extraordinarily well. And we still largely don't know why. A new paper from Jamie Simon, Daniel Kunin, and 12 co-authors argues that a scientific theory of deep learning is emerging, and coins a name for the emerging field: learning mechanics. We sat down with Jamie and Dan on Generally Intelligent to talk about what a physics of deep learning would actually look like, why now, and what's left to figure out. 3:05 Learning mechanics as the physics to mechanistic interpretability's biology 4:13 Why deep learning needs a theory 7:07 Why deep learning is uniquely hard to engineer 12:11 How a week in the woods became a paper 25:59 The barrier to theory isn't opacity, but complexity 36:26 Deep learning's first gas law 47:22 Why more particles makes the problem easier 56:22 The discretization hypothesis 1:01:50 The strongest signal that a compact theory exists 1:05:07 The Platonic Representation Hypothesis 1:15:41 Why learning mechanics and mech interp need each other 1:25:29 Theory as safety infrastructure

Imbue

18,159 views • 3 months ago

7th day boxing training. Learning the basics and improving daily, JAKE PAUL I’m coming for ya ya big juicehead 🔥🏆

7th day boxing training. Learning the basics and improving daily, JAKE PAUL I’m coming for ya ya big juicehead 🔥🏆

HSTikkyTokky

3,919,048 views • 1 year ago

SPOILERS FOR SURVIVING BARSTOOL It's Episode 12 and Paul Bissonnette is just learning the rules Better late than never! Tommy John

SPOILERS FOR SURVIVING BARSTOOL It's Episode 12 and Paul Bissonnette is just learning the rules Better late than never! Tommy John

Barstool Sports

210,556 views • 1 year ago

It’s a common saying that the day you stop learning is the day you start dying. If you want to stay relevant and stay on top, you must commit to learning and personal development always. Do you desire to live a life of excellence? Then commit to learning. #BishopDavidAbioye

It’s a common saying that the day you stop learning is the day you start dying. If you want to stay relevant and stay on top, you must commit to learning and personal development always. Do you desire to live a life of excellence? Then commit to learning. #BishopDavidAbioye

Bishop David Abioye

11,755 views • 1 year ago

Ajeet Bharti roasting Alok 'Mandal simper' Bhatt (Alok Bhatt) and Kaustubh Masterstrokevaadi Kaustubh Raje 🇮🇳 on The Chronology of Deep State. RW is learning about Reformists doglapan.

Ajeet Bharti roasting Alok 'Mandal simper' Bhatt (Alok Bhatt) and Kaustubh Masterstrokevaadi Kaustubh Raje 🇮🇳 on The Chronology of Deep State. RW is learning about Reformists doglapan.

Based Monk 📢(#Unreserved)

67,206 views • 1 year ago

THIS IS WHAT CHURCH IS ALL ABOUT! FROM BEING BROUGHT IN CHAINS TO LEARNING A SKILL, OPENING A BUSINESS AND BEING SPONSORED IN THE UNIVERSITY BY DRS PASTORS PAUL AND BECKY PAUL-ENENCHE - Testimony by Sis. Faith Adama #DrPaulEnenche #DrMrsBeckyPaulEnenche #DIGC #Dominion2025 #GloryDome #SupersonicSunday #23rdMarch2025 #ChurchGist

THIS IS WHAT CHURCH IS ALL ABOUT! FROM BEING BROUGHT IN CHAINS TO LEARNING A SKILL, OPENING A BUSINESS AND BEING SPONSORED IN THE UNIVERSITY BY DRS PASTORS PAUL AND BECKY PAUL-ENENCHE - Testimony by Sis. Faith Adama #DrPaulEnenche #DrMrsBeckyPaulEnenche #DIGC #Dominion2025 #GloryDome #SupersonicSunday #23rdMarch2025 #ChurchGist

therealchurchgist

13,362 views • 1 year ago

Connor is just learning about Tommy and Dante spending $3,500 on champagne so the bottle girls will hang out with them

Connor is just learning about Tommy and Dante spending $3,500 on champagne so the bottle girls will hang out with them

Barstool Spring Break

167,488 views • 3 months ago

Excited to share Unit 10, the finale of my latest course! 🎉 My aim is to provide a modern take on learning deep learning & AI using open-source libraries. And I hope you enjoyed the journey from backpropagation to implementing LLMs in PyTorch!

Excited to share Unit 10, the finale of my latest course! 🎉 My aim is to provide a modern take on learning deep learning & AI using open-source libraries. And I hope you enjoyed the journey from backpropagation to implementing LLMs in PyTorch!

Sebastian Raschka

69,415 views • 3 years ago

AI is so smart, why are its internals 'spaghetti'? We spoke with Kenneth Stanley and Akarsh Kumar (MIT) about their new paper: Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis. Co-authors: Jeff Clune Joel Lehman

AI is so smart, why are its internals 'spaghetti'? We spoke with Kenneth Stanley and Akarsh Kumar (MIT) about their new paper: Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis. Co-authors: Jeff Clune Joel Lehman

Machine Learning Street Talk

84,446 views • 1 year ago

Three years ago, I started working on an easy-to-use tool for interpretable machine learning in science. I wanted it to do for symbolic regression what Theano did for deep learning. Today, I am beyond excited to share with you the paper describing it! 1.

Three years ago, I started working on an easy-to-use tool for interpretable machine learning in science. I wanted it to do for symbolic regression what Theano did for deep learning. Today, I am beyond excited to share with you the paper describing it! 1.

Miles Cranmer

240,375 views • 3 years ago

💥 What AI means for your product strategy with Paul Adams (Paul Adams) Paul is Chief Product Officer at Intercom, where he leads product management, product design, data science, and research. Paul is a deep thinker, and has an incredibly diverse background, having been global head of brand design at Facebook, a senior user researcher at Google, and a product designer at Dyson. In our conversation, Paul shares: ➊ Practical advice for integrating AI into your organization and product ➋ Tips and tools for learning AI as a PM ❸ Hilarious stories from Google and Facebook ❹ How to build conviction with skeptical coworkers ➎ Lessons learned from pricing at Intercom ➏ How Intercom thinks about JTBD ➐ Much more

Lenny Rachitsky

33,276 views • 2 years ago

One of my main learning beliefs: there is no distinction between 'foundation' or 'basic' exercises and 'advanced' exercises. Creating a 'difficulty' gradient that you must 'ascend' limits so much learning, and makes people intimidated to even think about trying various things.

One of my main learning beliefs: there is no distinction between 'foundation' or 'basic' exercises and 'advanced' exercises. Creating a 'difficulty' gradient that you must 'ascend' limits so much learning, and makes people intimidated to even think about trying various things.

tomfoxdraws

68,827 views • 8 months ago

Who is your favourite 2010s Arsenal midfielder? In our second pod with Isaac Hayden, he talks Arsene Wenger, Mikel Arteta and learning his craft at Arsenal. ❤️

Who is your favourite 2010s Arsenal midfielder? In our second pod with Isaac Hayden, he talks Arsene Wenger, Mikel Arteta and learning his craft at Arsenal. ❤️

James Allcott

18,168 views • 5 months ago

Learning how to save lives❤️‍🩹 Thank you American Heart Texas and Paul "Bear" Bryant Awards for showing us a valuable skill that can save a life!

Learning how to save lives❤️‍🩹 Thank you American Heart Texas and Paul "Bear" Bryant Awards for showing us a valuable skill that can save a life!

Houston Football

11,517 views • 21 days ago

DID YOU KNOW: Disney had previously released four 'Winnie the Pooh' straight-to-DVD specials with stories about learning called 'Disney Learning Adventures'. The fifth and sixth specials/DVDs were canceled before release but were seemingly completed according to this trailer.

DID YOU KNOW: Disney had previously released four 'Winnie the Pooh' straight-to-DVD specials with stories about learning called 'Disney Learning Adventures'. The fifth and sixth specials/DVDs were canceled before release but were seemingly completed according to this trailer.

Lost Media Busters

22,084 views • 1 year ago