#144 Why is Bayesian Deep Learning so Powerful, with Maurizio Filippone

https://is1-ssl.mzstatic.com/image/thumb/Podcasts123/v4/80/8d/db/808ddbb6-a199-09fd-48f1-a652716cb5ec/mza_15228831011262537697.jpg/600x600bb.jpg

Learning Bayesian Statistics

Alexandre Andorra

183 episodes

20 hours ago

Are you a researcher or data scientist / analyst / ninja? Do you want to learn Bayesian inference, stay up to date or simply want to understand what Bayesian inference is?

Then this podcast is for you! You'll hear from researchers and practitioners of all fields about how they use Bayesian statistics, and how in turn YOU can apply these methods in your modeling workflow.

When I started learning Bayesian methods, I really wished there were a podcast out there that could introduce me to the methods, the projects and the people who make all that possible.

So I created "Learning Bayesian Statistics", where you'll get to hear how Bayesian statistics are used to detect black matter in outer space, forecast elections or understand how diseases spread and can ultimately be stopped. But this show is not only about successes -- it's also about failures, because that's how we learn best.

So you'll often hear the guests talking about what *didn't* work in their projects, why, and how they overcame these challenges. Because, in the end, we're all lifelong learners!

My name is Alex Andorra by the way. By day, I'm a Senior data scientist. By night, I don't (yet) fight crime, but I'm an open-source enthusiast and core contributor to the python packages PyMC and ArviZ. I also love Nutella, but I don't like talking about it – I prefer eating it.

So, whether you want to learn Bayesian statistics or hear about the latest libraries, books and applications, this podcast is for you -- just subscribe! You can also support the show and unlock exclusive Bayesian swag on Patreon!

Technology

Science

RSS

All content for Learning Bayesian Statistics is the property of Alexandre Andorra and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Are you a researcher or data scientist / analyst / ninja? Do you want to learn Bayesian inference, stay up to date or simply want to understand what Bayesian inference is?

When I started learning Bayesian methods, I really wished there were a podcast out there that could introduce me to the methods, the projects and the people who make all that possible.

So you'll often hear the guests talking about what *didn't* work in their projects, why, and how they overcame these challenges. Because, in the end, we're all lifelong learners!

Technology

Science

https://hosting-media.rs-prod.riverside.fm/media/imports/podcasts/79e0a4fb-97ab-4e95-a875-24a8b9ee27da/episodes/d065ee4e-476f-4981-86f8-a264f05616f3/episode-144-square.jpg

#144 Why is Bayesian Deep Learning so Powerful, with Maurizio Filippone

Learning Bayesian Statistics

1 hour 28 minutes 22 seconds

2 months ago

#144 Why is Bayesian Deep Learning so Powerful, with Maurizio Filippone

Sign up for Alex's first live cohort, about Hierarchical Model building!
Get 25% off "Building AI Applications for Data Scientists and Software Engineers"

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

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:

Why GPs still matter: Gaussian Processes remain a go-to for function estimation, active learning, and experimental design – especially when calibrated uncertainty is non-negotiable.
Scaling GP inference: Variational methods with inducing points (as in GPflow) make GPs practical on larger datasets without throwing away principled Bayes.
MCMC in practice: Clever parameterizations and gradient-based samplers tighten mixing and efficiency; use MCMC when you need gold-standard posteriors.
Bayesian deep learning, pragmatically: Stochastic-gradient training and approximate posteriors bring Bayesian ideas to neural networks at scale.
Uncertainty that ships: Monte Carlo dropout and related tricks provide fast, usable uncertainty – even if they’re approximations.
Model complexity ≠ model quality: Understanding capacity, priors, and inductive bias is key to getting trustworthy predictions.
Deep Gaussian Processes: Layered GPs offer flexibility for complex functions, with clear trade-offs in interpretability and compute.
Generative models through a Bayesian lens: GANs and friends benefit from explicit priors and uncertainty – useful for safety and downstream decisions.
Tooling that matters: Frameworks like GPflow lower the friction from idea to implementation, encouraging reproducible, well-tested modeling.
Where we’re headed: The future of ML is uncertainty-aware by default – integrating UQ tightly into optimization, design, and deployment.

Chapters:

08:44 Function Estimation and Bayesian Deep Learning

10:41 Understanding Deep Gaussian Processes

25:17 Choosing Between Deep GPs and Neural Networks

32:01 Interpretability and Practical Tools for GPs

43:52 Variational Methods in Gaussian Processes

54:44 Deep Neural Networks and Bayesian Inference

01:06:13 The Future of Bayesian Deep Learning

01:12:28 Advice for Aspiring Researchers