Today's clip is from<a rel="noopener noreferrer nofollow" href="https://learnbayesstats.com/episode/151-diffusion-models-in-python-a-live-demo-with-jonas-arruda" target="_blank"> Episode 151</a> of the podcast, with Jonas Arruda In this conversation, Jonas Arruda explains how diffusion models generate data by learning to reverse a noise process. The idea is to start from a simple distribution like Gaussian noise and gradually remove noise until the target distribution emerges. This is done through a forward process that adds noise to clean parameters and a backward process that learns how to undo that corruption. A noise schedule controls how much noise is added or removed at each step, guiding the transformation from pure randomness back to meaningful structure. Get the full discussion <a rel="noopener noreferrer nofollow" href="https://learnbayesstats.com/episode/151-diffusion-models-in-python-a-live-demo-with-jonas-arruda" target="_blank">here</a> • Join this channel to get access to perks: <a rel="noopener noreferrer nofollow" href="https://www.patreon.com/c/learnbayesstats" target="_blank">https://www.patreon.com/c/learnbayesstats</a> • Intro to Bayes Course (first 2 lessons free): <a rel="noopener noreferrer nofollow" href="https://topmate.io/alex_andorra/503302" target="_blank">https://topmate.io/alex_andorra/503302</a> • Advanced Regression Course (first 2 lessons free): <a rel="noopener noreferrer nofollow" href="https://topmate.io/alex_andorra/1011122" target="_blank">https://topmate.io/alex_andorra/1011122</a> Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at <a rel="noopener noreferrer nofollow" href="https://bababrinkman.com/" target="_blank">https://bababrinkman.com/</a> !

Today's clip is from Episode 151 of the podcast, with Jonas ArrudaIn this conversation, Jonas Arruda explains how diffusion models generate data by learning to reverse a noise process. The idea is to start from a simple distribution like Gaussian noise and gradually remove noise until the target distribution emerges. This is done through a forward process that adds noise to clean parameters and a backward process that learns how to undo that corruption. A noise schedule controls how much noise is added or removed at each step, guiding the transformation from pure randomness back to meaningful structure.Get the full discussion here• Join this channel to get access to perks:https://www.patreon.com/c/learnbayesstats• Intro to Bayes Course (first 2 lessons free): https://topmate.io/alex_andorra/503302• Advanced Regression Course (first 2 lessons free): https://topmate.io/alex_andorra/1011122Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !

Today's clip is from<a href="https://learnbayesstats.com/episode/151-diffusion-models-in-python-a-live-demo-with-jonas-arruda" rel="noopener noreferrer"> Episode 151</a> of the podcast, with Jonas Arruda In this conversation, Jonas Arruda explains how diffusion models generate data by learning to reverse a noise process. The idea is to start from a simple distribution like Gaussian noise and gradually remove noise until the target distribution emerges. This is done through a forward process that adds noise to clean parameters and a backward process that learns how to undo that corruption. A noise schedule controls how much noise is added or removed at each step, guiding the transformation from pure randomness back to meaningful structure. Get the full discussion <a href="https://learnbayesstats.com/episode/151-diffusion-models-in-python-a-live-demo-with-jonas-arruda" rel="noopener noreferrer">here</a> • Join this channel to get access to perks: <a href="https://www.patreon.com/c/learnbayesstats" rel="noopener noreferrer">https://www.patreon.com/c/learnbayesstats</a> • Intro to Bayes Course (first 2 lessons free): <a href="https://topmate.io/alex_andorra/503302" rel="noopener noreferrer">https://topmate.io/alex_andorra/503302</a> • Advanced Regression Course (first 2 lessons free): <a href="https://topmate.io/alex_andorra/1011122" rel="noopener noreferrer">https://topmate.io/alex_andorra/1011122</a> Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at <a href="https://bababrinkman.com/" rel="noopener noreferrer">https://bababrinkman.com/</a> !

BITESIZE | How Do Diffusion Models Work?

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 <a rel="noopener noreferrer nofollow" href="https://alexandorra.github.io/" target="_blank">Alex Andorra</a> 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 <a rel="noopener noreferrer nofollow" href="https://docs.pymc.io/" target="_blank">PyMC</a> and <a rel="noopener noreferrer nofollow" href="https://arviz-devs.github.io/arviz/" target="_blank">ArviZ</a>. 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 <a rel="noopener noreferrer nofollow" href="https://www.patreon.com/learnbayesstats" target="_blank">unlock exclusive Bayesian swag on Patreon</a>!

Science

Technology

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!

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 <a href="https://alexandorra.github.io/" rel="noopener noreferrer">Alex Andorra</a> 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 <a href="https://docs.pymc.io/" rel="noopener noreferrer">PyMC</a> and <a href="https://arviz-devs.github.io/arviz/" rel="noopener noreferrer">ArviZ</a>. 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 <a href="https://www.patreon.com/learnbayesstats" rel="noopener noreferrer">unlock exclusive Bayesian swag on Patreon</a>!

Share BITESIZE | How Do Diffusion Models Work?

Sign up to save your podcasts

BITESIZE | How Do Diffusion Models Work?

BITESIZE | How Do Diffusion Models Work?

More shows like Learning Bayesian Statistics

Odd Lots

Conversations with Tyler

Talk Python To Me

The Quanta Podcast

Super Data Science: ML & AI Podcast with Jon Krohn

Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas

Practical AI

Last Week in AI

Machine Learning Street Talk (MLST)

Dwarkesh Podcast

Hard Fork

Latent Space: The AI Engineer Podcast

Risky Business with Nate Silver and Maria Konnikova

Prof G Markets

The Opinions