Practical AI: Machine Learning, Data Science, LLM cover image

Practical AI: Machine Learning, Data Science, LLM

Latest episodes

undefined
Sep 25, 2019 • 46min

The influence of open source on AI development

The All Things Open conference is happening soon, and we snagged one of their speakers to discuss open source and AI. Samuel Taylor talks about the essential role that open source is playing in AI development and research, and he gives us some tips on choosing AI-related side projects. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – DigitalOcean now offers three managed databases — PostgreSQL, MySQL, and Redis. Get started for free with a $50 credit. Learn more at do.co/changelog. The Brave Browser – Browse the web up to 8x faster than Chrome and Safari, block ads and trackers by default, and reward your favorite creators with the built-in Basic Attention Token. Download Brave for free and give tipping a try right here on changelog.com. All Things Open – Exploring open source, open tech, and the open web in the enterprise. Raleigh, NC — October 13-15, 2019 Featuring:Samuel Taylor – Twitter, GitHub, LinkedIn, WebsiteChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes:Tweet and mention @Changelog or @PracticalAIFM for a chance to win 1 of 5 free passes to the conference! “I want a free pass to @AllThingsOpen because…” All Things Open Samuel’s All Things Open talk description Episode #17 - Fighting bias in hiring Jupyter Pandas Scikit-learn Something missing or broken? PRs welcome!
undefined
Sep 17, 2019 • 48min

Worlds are colliding - AI and HPC

In this very special fully-connected episode of Practical AI, Daniel interviews Chris. They discuss High Performance Computing (HPC) and how it is colliding with the world of AI. Chris explains how HPC differs from cloud/on-prem infrastructure, and he highlights some of the challenges of an HPC-based AI strategy. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – DigitalOcean now offers three managed databases — PostgreSQL, MySQL, and Redis. Get started for free with a $50 credit. Learn more at do.co/changelog. The Brave Browser – Browse the web up to 8x faster than Chrome and Safari, block ads and trackers by default, and reward your favorite creators with the built-in Basic Attention Token. Download Brave for free and give tipping a try right here on changelog.com. Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com. Rollbar – We move fast and fix things because of Rollbar. Resolve errors in minutes. Deploy with confidence. Learn more at rollbar.com/changelog. Featuring:Chris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: HPC course on Udacity Google Colab SIParCS internship at NCAR Something missing or broken? PRs welcome!
undefined
Sep 9, 2019 • 59min

AutoML and AI at Google

We’re talking with Sherol Chen, a machine learning developer, about AI at Google and AutoML methods. Sherol explains how the various AI groups within Google work together and how AutoML fits into that puzzle. She also explains how to get started with AutoML step-by-step (this is “practical” AI after all). Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – DigitalOcean now offers three managed databases — PostgreSQL, MySQL, and Redis. Get started for free with a $50 credit. Learn more at do.co/changelog. Changelog Weekly – We track, log, and contextualize what’s happening in software throughout the week and deliver it directly to your inbox on Sunday mornings. Head to changelog.com/weekly to browse the archives, subscribe, and push the easy button on your continuing education. Brain Science – For the curious! Brain Science is our new podcast exploring the inner-workings of the human brain to understand behavior change, habit formation, mental health, and being human. It’s Brain Science applied — not just how does the brain work, but how do we apply what we know about the brain to transform our lives. Featuring:Sherol Chen – Twitter, GitHub, LinkedIn, WebsiteChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Google cloud Google AI Tensorflow Quoc V. Le’s research Cloud AutoML Something missing or broken? PRs welcome!
undefined
Aug 26, 2019 • 56min

On being humAIn

David Yakobovitch joins the show to talk about the evolution of data science tools and techniques, the work he’s doing to teach these things at Galvanize, what his HumAIn Podcast is all about, and more. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – The simplest cloud platform for developers and teams Whether you’re running one virtual machine or ten thousand, makes managing your infrastructure too easy. Get started for free with a $50 credit. Learn more at do.co/changelog. Brain Science – For the curious! Brain Science is our new podcast exploring the inner-workings of the human brain to understand behavior change, habit formation, mental health, and being human. It’s Brain Science applied — not just how does the brain work, but how do we apply what we know about the brain to transform our lives. Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com. Featuring:David Yakobovitch – Twitter, LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Galvanize HumAIn Podcast Books “The Big Nine” by Amy Webb Something missing or broken? PRs welcome!
undefined
Aug 12, 2019 • 46min

Serving deep learning models with RedisAI

Redis is a an open source, in-memory data structure store, widely used as a database, cache and message broker. It now also support tensor data types and deep learning models via the RedisAI module. Why did they build this module? Who is or should be using it? We discuss this and much more with Pieter Cailliau. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – The simplest cloud platform for developers and teams Whether you’re running one virtual machine or ten thousand, makes managing your infrastructure too easy. Get started for free with a $50 credit. Learn more at do.co/changelog. Brain Science – For the curious! Brain Science is our new podcast exploring the inner-workings of the human brain to understand behavior change, habit formation, mental health, and being human. It’s Brain Science applied — not just how does the brain work, but how do we apply what we know about the brain to transform our lives. Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com. Featuring:Pieter Cailliau – Twitter, GitHub, LinkedIn, WebsiteChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Redis Redis modules RedisAI Hangar Hangar on GitHub Something missing or broken? PRs welcome!
undefined
Jul 30, 2019 • 55min

AI-driven studies of the ancient world and good GANs

Chris and Daniel take the opportunity to catch up on some recent AI news. Among other things, they discuss the increasing impact of AI on studies of the ancient world and “good” uses of GANs. They also provide some more learning resources to help you level up your AI and machine learning game. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – The simplest cloud platform for developers and teams Whether you’re running one virtual machine or ten thousand, makes managing your infrastructure too easy. Get started for free with a $50 credit. Learn more at do.co/changelog. DataEngPodcast – A podcast about data engineering and modern data infrastructure. Brain Science – For the curious! Brain Science is our new podcast exploring the inner-workings of the human brain to understand behavior change, habit formation, mental health, and being human. It’s Brain Science applied — not just how does the brain work, but how do we apply what we know about the brain to transform our lives. Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com. Featuring:Chris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes:AI is impacting studies of the ancient world: Machine learning has been used to automatically translate long-lost languages: Machine learning is about to revolutionize the study of ancient games: Others studies: Deep Learning for Classical Japanese Literature: In Codice Ratio: Machine Transcription in the Vatican Secret Archive: Reading Medieval Manuscripts with Deep Learning Technology: The AI technique that could imbue machines with the ability to reason A new way to use the AI behind deepfakes could improve cancer diagnosis: AIs are playing more games: DeepMind AI is secretly lurking on the public StarCraft II 1v1 ladder An unbeatable poker bot offers glimpses of video game AI’s future Relevant learning resources: NumPy implementations of a bunch of models (from scratch): Great new-ish NLP courses: Advanced NLP with spacy: New fast.ai course! A Code-First Introduction to NLP: Google Cloud - Deep Learning Containers Books “The Pragmatic Programmer” by David Thomas and Andrew Hunt “Data Science from Scratch” by Joel Grus Something missing or broken? PRs welcome!
undefined
Jul 19, 2019 • 53min

AI code that facilitates good science

We’re talking with Joel Grus, author of Data Science from Scratch, 2nd Edition, senior research engineer at the Allen Institute for AI (AI2), and maintainer of AllenNLP. We discussed Joel’s book, which has become a personal favorite of the hosts, and why he decided to approach data science and AI “from scratch.” Joel also gives us a glimpse into AI2, an introduction to AllenNLP, and some tips for writing good research code. This episode is packed full of reproducible AI goodness! Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – The simplest cloud platform for developers and teams Whether you’re running one virtual machine or ten thousand, makes managing your infrastructure too easy. Get started for free with a $50 credit. Learn more at do.co/changelog. DataEngPodcast – A podcast about data engineering and modern data infrastructure. Brain Science – For the curious! Brain Science is our new podcast exploring the inner-workings of the human brain to understand behavior change, habit formation, mental health, and being human. It’s Brain Science applied — not just how does the brain work, but how do we apply what we know about the brain to transform our lives. Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com. Featuring:Joel Grus – TwitterChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Allen AI AllenNLP AllenNLP demo website Writing Code for NLP Research​ I don’t like Notebooks Joel’s website Adversarial learning podcast Books “Data Science from Scratch” by Joel Grus Something missing or broken? PRs welcome!
undefined
Jul 3, 2019 • 51min

Celebrating episode 50 and the neural net!

Woo hoo! As we celebrate reaching episode 50, we come full circle to discuss the basics of neural networks. If you are just jumping into AI, then this is a great primer discussion with which to take that leap. Our commitment to making artificial intelligence practical, productive, and accessible to everyone has never been stronger, so we invite you to join us for the next 50 episodes! Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Featuring:Chris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes:Learn more about neural networks with the following learning resources. Books “Deep Learning” by Ian Goodfellow, Yoshua Bengio, and Aaron Courville “Data Science from Scratch” by Joel Grus There are literally too many others to name… Online Courses fast.ai MOOC Deep Learning course by Google on Udacity (free) Practical Machine Learning with TensorFlow 2.0 Alpha (free Udacity course) deeplearning.ai Deep Learning Specialization Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning (free Coursera course for TensorFlow 2) Intro to TensorFlow for Deep Learning by TensorFlow (free Udacity course for TensorFlow 2) Websites Microsoft AI School TensorFlow 2 Docs Amazon Machine Learning Training PyTorch Facebook AI Google AI Something missing or broken? PRs welcome!
undefined
Jun 25, 2019 • 55min

Exposing the deception of DeepFakes

This week we bend reality to expose the deceptions of deepfake videos. We talk about what they are, why they are so dangerous, and what you can do to detect and resist their insidious influence. In a political environment rife with distrust, disinformation, and conspiracy theories, deepfakes are being weaponized and proliferated as the latest form of state-sponsored information warfare. Join us for an episode scarier than your favorite horror movie, because this AI bogeyman is real! Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – Check out DigitalOcean’s dedicated vCPU Droplets with dedicated vCPU threads. Get started for free with a $50 credit. Learn more at do.co/changelog. DataEngPodcast – A podcast about data engineering and modern data infrastructure. Brain Science – For the curious! Brain Science is our new podcast exploring the inner-workings of the human brain to understand behavior change, habit formation, mental health, and being human. It’s Brain Science applied — not just how does the brain work, but how do we apply what we know about the brain to transform our lives. Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com. Featuring:Chris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: The Dark Knight’s Tale (DeepFake) Official PyTorch Implementation of StarGAN - CVPR 2018 Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (YouTube) Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (PDF) MelNet: A Generative Model for Audio in the Frequency Domain Text-based Editing of Talking-head Video Better Language Models and Their Implications (GPT-2) Fake-porn videos are being weaponized to harass and humiliate women: ‘Everybody is a potential target’ The National Security Challenges of Artificial Intelligence, Manipulated Media, and “Deepfakes” – 13 June 2019 Student with access to TPU credits reproduced GPT2-1.5B and plan to release model Papers With Code: fake+detection In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking A Retrospective Analysis of the Fake News Challenge Stance Detection Task Deepfake debunking tool may protect presidential candidates. For now. Sometimes The Era of Fake Videos is Here S.3805 - Malicious Deep Fake Prohibition Act of 2018 Practical AI episode #47 - GANs, RL, and transfer learning oh my! Synthetic Realities: Deep Learning for Detecting AudioVisual Fakes Machine Learning for fake news detection: theory and practice Something missing or broken? PRs welcome!
undefined
Jun 17, 2019 • 44min

Model inspection and interpretation at Seldon

Interpreting complicated models is a hot topic. How can we trust and manage AI models that we can’t explain? In this episode, Janis Klaise, a data scientist with Seldon, joins us to talk about model interpretation and Seldon’s new open source project called Alibi. Janis also gives some of his thoughts on production ML/AI and how Seldon addresses related problems. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:DigitalOcean – Check out DigitalOcean’s dedicated vCPU Droplets with dedicated vCPU threads. Get started for free with a $50 credit. Learn more at do.co/changelog. DataEngPodcast – A podcast about data engineering and modern data infrastructure. Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com. Featuring:Janis Klaise – Twitter, GitHub, LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Seldon Seldon Core Alibi Books “The Foundation Series” by Isaac Asimov “Interpretable Machine Learning” by Christoph Molnar Something missing or broken? PRs welcome!

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode