Learning Bayesian Statistics

#129 Bayesian Deep Learning & AI for Science with Vincent Fortuin

Apr 2, 2025

Vincent Fortuin, a tenure-track research leader at Helmholtz AI, dives into the world of Bayesian deep learning and its transformative power in scientific research. He discusses the contradictions in AI hype versus practical outcomes and highlights how combining Bayesian statistics with deep learning enhances prediction reliability. Fortuin emphasizes the significance of prior knowledge and argues for better uncertainty communication in AI applications. He also touches on innovative techniques that improve data efficiency and acknowledges the need for collaboration in the community.

01:02:43

Creator website

Episode guests

Vincent Fortuin

AI Summary

AI Chapters

Episode notes

Podcast summary created with Snipd AI

Quick takeaways

Bayesian deep learning combines prior knowledge and uncertainty quantification, leading to more reliable predictions in scientific applications.

Recent advancements in efficient inference techniques, like Laplace and subspace inference, enhance computational performance in Bayesian models.

The integration of domain knowledge through Bayesian methods aids decision-making processes in critical fields like healthcare and scientific experimentation.

Deep dives

The Limitations of Traditional Deep Learning in Science

Traditional deep learning often faces challenges when applied to scientific contexts due to its inability to incorporate prior knowledge and quantify uncertainty. Consequently, researchers like Vincent Fortwin advocate for Bayesian deep learning, which integrates prior information into models, leading to more reliable predictions. This enhancement is indispensable in scientific applications that require careful decision-making based on model output. By addressing these limitations, Bayesian deep learning can achieve better calibration and foster insights that purely empirical models may overlook.

Intro

4min

Navigating the Shift: From Biochemistry to Bayesian Deep Learning

12min

Navigating Bayesian Deep Learning

22min

Efficient Algorithms in Bayesian Deep Learning

6min

Innovative Neural Network Techniques for MCMC Initialization

4min

Enhancing AI Reliability Through Uncertainty Communication

3min

Building a Career in Deep Learning

8min

Concluding Thoughts and Resources for Bayesian Enthusiasts

2min

Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch!

Intro to Bayes Course (first 2 lessons free)
Advanced Regression Course (first 2 lessons free)

Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!

Visit our Patreon page to unlock exclusive Bayesian swag ;)

Takeaways:

The hype around AI in science often fails to deliver practical results.
Bayesian deep learning combines the strengths of deep learning and Bayesian statistics.
Fine-tuning LLMs with Bayesian methods improves prediction calibration.
There is no single dominant library for Bayesian deep learning yet.
Real-world applications of Bayesian deep learning exist in various fields.
Prior knowledge is crucial for the effectiveness of Bayesian deep learning.
Data efficiency in AI can be enhanced by incorporating prior knowledge.
Generative AI and Bayesian deep learning can inform each other.
The complexity of a problem influences the choice between Bayesian and traditional deep learning.
Meta-learning enhances the efficiency of Bayesian models.
PAC-Bayesian theory merges Bayesian and frequentist ideas.
Laplace inference offers a cost-effective approximation.
Subspace inference can optimize parameter efficiency.
Bayesian deep learning is crucial for reliable predictions.
Effective communication of uncertainty is essential.
Realistic benchmarks are needed for Bayesian methods
Collaboration and communication in the AI community are vital.

Chapters:

00:00 Introduction to Bayesian Deep Learning

06:12 Vincent's Journey into Machine Learning

12:42 Defining Bayesian Deep Learning

17:23 Current Landscape of Bayesian Libraries

22:02 Real-World Applications of Bayesian Deep Learning

24:29 When to Use Bayesian Deep Learning

29:36 Data Efficient AI and Generative Modeling

31:59 Exploring Generative AI and Meta-Learning

34:19 Understanding Bayesian Deep Learning and Prior Knowledge

39:01 Algorithms for Bayesian Deep Learning Models

43:25 Advancements in Efficient Inference Techniques

49:35 The Future of AI Models and Reliability

52:47 Advice for Aspiring Researchers in AI

56:06 Future Projects and Research Directions

Thank you to my Patrons for making this episode possible!

Yusuke Saito, Avi Bryant, Ero Carrera, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, William Benton, James Ahloy, Robin Taylor,, Chad Scherrer, Zwelithini Tunyiswa, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Ian Moran, Paul Oreto, Colin Caprani, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Marcin Elantkowski, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Philippe Labonde, Michael Hankin, Cameron Smith, Tomáš Frýda, Ryan Wesslen, Andreas Netti, Riley King, Yoshiyuki Hamajima, Sven De Maeyer, Michael DeCrescenzo, Fergal M, Mason Yahr, Naoya Kanai, Steven Rowland, Aubrey Clayton, Jeannine Sue, Omri Har Shemesh, Scott Anthony Robson, Robert Yolken, Or Duek, Pavel Dusek, Paul Cox, Andreas Kröpelin, Raphaël R, Nicolas Rode, Gabriel Stechschulte, Arkady, Kurt TeKolste, Gergely Juhasz, Marcus Nölke, Maggi Mackintosh, Grant Pezzolesi, Avram Aelony, Joshua Meehl, Javier Sabio, Kristian Higgins, Alex Jones, Gregorio Aguilar, Matt Rosinski, Bart Trudeau, Luis Fonseca, Dante Gates, Matt Niccolls, Maksim Kuznecov, Michael Thomas, Luke Gorrie, Cory Kiser, Julio, Edvin Saveljev, Frederick Ayala, Jeffrey Powell, Gal Kampel, Adan Romero, Will Geary, Blake Walters, Jonathan Morgan, Francesco Madrisotti, Ivy Huang, Gary Clarke, Robert Flannery, Rasmus Hindström, Stefan, Corey Abshire, Mike Loncaric, David McCormick, Ronald Legere, Sergio Dolia, Michael Cao, Yiğit Aşık and Suyog Chandramouli.

Links from the show:

Vincent’s website: https://fortuin.github.io/
Vincent on Linkedin: https://www.linkedin.com/in/vincent-fortuin-42426b134/
Vincent on GitHub: https://github.com/fortuin
Vincent on Medium: https://medium.com/@vincefort
Vincent on BlueSky: https://bsky.app/profile/vincefort.bsky.social
LBS #107 Amortized Bayesian Inference with Deep Neural Networks, with Marvin Schmitt: https://learnbayesstats.com/episode/107-amortized-bayesian-inference-deep-neural-networks-marvin-schmitt/
Position paper on Bayesian deep learning: https://proceedings.mlr.press/v235/papamarkou24b.html
Position paper on generative AI: https://arxiv.org/abs/2403.00025
BNN review paper: https://arxiv.org/abs/2309.16314
Priors in BDL review paper: https://onlinelibrary.wiley.com/doi/10.1111/insr.12502
BayesFlow: https://bayesflow.org/
BayesianTorch: https://github.com/IntelLabs/bayesian-torch
Laplace Torch: https://aleximmer.github.io/Laplace/
TyXe: https://github.com/TyXe-BDL/TyXe
Introduction to PAC-Bayes: https://arxiv.org/abs/2110.11216
Training GPT2 with Bayesian methods: https://proceedings.mlr.press/v235/shen24b.html
Bayesian fine-tuning for LLMs: https://arxiv.org/abs/2405.03425
Try out NormalizingFlow initialization with Nutpie: https://discourse.pymc.io/t/new-experimental-sampling-algorithm-fisher-hmc-in-nutpie-for-pymc-and-stan-models/16114/5

Transcript

This is an automatic transcript and may therefore contain errors. Please get in touch if you're willing to correct them.

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.

Learning Bayesian Statistics

#129 Bayesian Deep Learning & AI for Science with Vincent Fortuin

Episode guests

Podcast summary created with Snipd AI

Quick takeaways

Deep dives

The Limitations of Traditional Deep Learning in Science

Advancements in Efficient Bayesian Inference Techniques

Importance of Prior Knowledge in Bayesian Deep Learning

The Role of Meta-Learning and Pac-Bayesian Theory

Challenges and Future Directions in Bayesian Deep Learning

Remember Everything You Learn from Podcasts