David Sweet, author of “Tuning Up: From A/B testing to Bayesian optimization”, introduces Dan and Chris to system tuning, and takes them from A/B testing to response surface methodology, contextual bandit, and finally bayesian optimization. Along the way, we get fascinating insights into recommender systems and high-frequency trading! Join the discussionChangelog++ members get a bonus 1 minute at the end of this episode and zero ads. Join today!Sponsors:O'Reilly Media – Learn by doing — Python, data, AI, machine learning, Kubernetes, Docker, and more. Just open your browser and dive in. Learn more and keep your teams’ skills sharp at oreilly.com/changelog RudderStack – Smart customer data pipeline made for developers. RudderStack is the smart customer data pipeline. Connect your whole customer data stack. Warehouse-first, open source Segment alternative. Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with no ads, extended episodes, outtakes, bonus content, a deep discount in our merch store (soon), and more to come. Let’s do this! 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 Sweet – Twitter, LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes:Books “Experimentation for Engineers” by David Sweet Tuning Up | GitHub Manning 40% discount code: podpracticalAI19 Something missing or broken? PRs welcome!

Our Slack community wanted to hear about AI-driven drug discovery, and we listened. Abraham Heifets from Atomwise joins us for a fascinating deep dive into the intersection of deep learning models and molecule binding. He describes how these methods work and how they are beginning to help create drugs for “undruggable” diseases! Join the discussionChangelog++ members save 4 minutes on this episode because they made the ads disappear. Join today!Sponsors:O'Reilly Media – Learn by doing — Python, data, AI, machine learning, Kubernetes, Docker, and more. Just open your browser and dive in. Learn more and keep your teams’ skills sharp at oreilly.com/changelog Code-ish by Heroku – A podcast from the team at Heroku, exploring code, technology, tools, tips, and the life of the developer. Check out episode 98 and episode 99 for insights on the ethical and technical sides of deep fakes. Subscribe on Apple Podcasts and Spotify. 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. Featuring:Abe Heifets – TwitterChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Atomwise Atomwise Receives a $2.3M Grant to Develop New Therapies for Drug Resistant Malaria and Tuberculosis Atomwise Partners with Global Research Teams to Pursue Broad-Spectrum Treatments Against COVID-19 and Future Coronavirus Outbreaks World robotic soccer Philadelphia chromosome Alphafold Canavan disease example: Paper: “Discovery of Novel Inhibitors of a Critical Brain Enzyme Using a Homology Model and a Deep Convolutional Neural Network” AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery [“Memorizing yesterday’s stock price” example](Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization) Something missing or broken? PRs welcome!

Empirical analysis from Roy Schwartz (Hebrew University of Jerusalem) and Jesse Dodge (AI2) suggests the AI research community has paid relatively little attention to computational efficiency. A focus on accuracy rather than efficiency increases the carbon footprint of AI research and increases research inequality. In this episode, Jesse and Roy advocate for increased research activity in Green AI (AI research that is more environmentally friendly and inclusive). They highlight success stories and help us understand the practicalities of making our workflows more efficient. Join the discussionChangelog++ members save 5 minutes on this episode because they made the ads disappear. Join today!Sponsors: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. Code-ish by Heroku – A podcast from the team at Heroku, exploring code, technology, tools, tips, and the life of the developer. Check out episode 98 and episode 99 for insights on the ethical and technical sides of deep fakes. Subscribe on Apple Podcasts and Spotify. Knowable – Learn from the world’s best minds, anytime, anywhere, and at your own pace through audio. Get unlimited access to every Knowable audio course right now. Click here to check it out and use code CHANGELOG for 20% off! Featuring:Roy Schwartz – Twitter, WebsiteJesse Dodge – TwitterChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Green AI article in the communications of the ACM Training a single AI model can emit as much carbon as five cars in their lifetimes Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping Parameter-Efficient Transfer Learning for NLP Reproducibility at EMNLP 2020 Something missing or broken? PRs welcome!

In this Fully-Connected episode, Chris and Daniel discuss low code / no code development, GPU jargon, plus more data leakage issues. They also share some really cool new learning opportunities for leveling up your AI/ML game! Join the discussionChangelog++ members get a bonus 3 minutes at the end of this episode and zero ads. Join today!Sponsors:Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with no ads, extended episodes, outtakes, bonus content, a deep discount in our merch store (soon), and more to come. Let’s do this! 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. Linode – Get $100 in free credit to get started on Linode – Linode is our cloud of choice and the home of Changelog.com. Head to linode.com/changelog OR text CHANGELOG to 474747 to get instant access to that $100 in free credit. Featuring:Chris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Follow up content from Rajiv Shah: Running code and failing models Rajiv’s previous episode Lambda Lab’s GPU benchmarks Machine Learning in Microsoft Excel Deep Learning at the Speed of Light MLCommons and MLCube: Previous episode about MLCommons MLCube project Learning Resources: Yann LeCun’s Deep Learning Course Is Now Free & Fully Online TensorFlow Everywhere Something missing or broken? PRs welcome!

Elad Walach of Aidoc joins Chris to talk about the use of AI for medical imaging interpretation. Starting with the world’s largest annotated training data set of medical images, Aidoc is the radiologist’s best friend, helping the doctor to interpret imagery faster, more accurately, and improving the imaging workflow along the way. Elad’s vision for the transformative future of AI in medicine clearly soothes Chris’s concern about managing his aging body in the years to come. ;-) Join the discussionChangelog++ members save 5 minutes on this episode because they made the ads disappear. Join today!Sponsors:Code-ish by Heroku – A podcast from the team at Heroku, exploring code, technology, tools, tips, and the life of the developer. Check out episode 98 and episode 99 for insights on the ethical and technical sides of deep fakes. Subscribe on Apple Podcasts and Spotify. 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. Knowable – Learn from the world’s best minds, anytime, anywhere, and at your own pace through audio. Get unlimited access to every Knowable audio course right now. Click here to check it out and use code CHANGELOG for 20% off! Featuring:Elad Walach – Twitter, LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteShow Notes: Aidoc | Website Aidoc Medical | LinkedIn Aidoc | Twitter Something missing or broken? PRs welcome!

John Myers of Gretel puts on his apron and rolls up his sleeves to show Dan and Chris how to cook up some synthetic data for automated data labeling, differential privacy, and other purposes. His military and intelligence community background give him an interesting perspective that piqued the interest of our intrepid hosts. Join the discussionChangelog++ members save 5 minutes on this episode because they made the ads disappear. Join today!Sponsors:Code-ish by Heroku – A podcast from the team at Heroku, exploring code, technology, tools, tips, and the life of the developer. Check out episode 101 for a deep dive with Cornelia Davis (CTO of Weaveworks) on cloud native, cloud native patterns, and what is really means to be a cloud native application. Subscribe on Apple Podcasts and Spotify. Knowable – Learn from the world’s best minds, anytime, anywhere, and at your own pace through audio. Get unlimited access to every Knowable audio course right now. Click here to check it out and use code CHANGELOG for 20% off! 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. Featuring:John Myers – LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Gretel | Website Gretel | LinkedIn Gretel | Twitter Gretel | Slack Gretel Synthetics | GitHub Gretel Blueprints | GitHub Gretel | Improving massively imbalanced datasets in machine learning with synthetic data Gretel | Deep dive on generating synthetic data for Healthcare Something missing or broken? PRs welcome!

Daniel and Chris sniff out the secret ingredients for collecting, displaying, and analyzing odor data with Terri Jordan and Yanis Caritu of Aryballe. It certainly smells like a good time, so join them for this scent-illating episode! Join the discussionChangelog++ members get a bonus 1 minute at the end of this episode and zero ads. Join today!Sponsors:Knowable – Learn from the world’s best minds, anytime, anywhere, and at your own pace through audio. Get unlimited access to every Knowable audio course right now. Click here to check it out and use code CHANGELOG for 20% off! Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with no ads, extended episodes, outtakes, bonus content, a deep discount in our merch store (soon), and more to come. Let’s do this! 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. Linode – Get $100 in free credit to get started on Linode – Linode is our cloud of choice and the home of Changelog.com. Head to linode.com/changelog OR text CHANGELOG to 474747 to get instant access to that $100 in free credit. Featuring:Terri Jordan – Twitter, LinkedInYanis Caritu – LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Aryballe Aryballe | Twitter Aryballe Hardware Solutions Aryballe Software & Data Platform How Machine Learning in Digital Olfaction Works Readying Odor Data For Reproduction Using Machine Learning Aryballe raises $7.9 million for odor-detecting AI sensors Something missing or broken? PRs welcome!

MLCommons launched in December 2020 as an open engineering consortium that seeks to accelerate machine learning innovation and broaden access to this critical technology for the public good. David Kanter, the executive director of MLCommons, joins us to discuss the launch and the ambitions of the organization. In particular we discuss the three pillars of the organization: Benchmarks and Metrics (e.g. MLPerf), Datasets and Models (e.g. People’s Speech), and Best Practices (e.g. MLCube). Join the discussionChangelog++ members save 5 minutes on this episode because they made the ads disappear. Join today!Sponsors:Code-ish by Heroku – A podcast from the team at Heroku, exploring code, technology, tools, tips, and the life of the developer. Check out episode 98 and episode 99 for insights on the ethical and technical sides of deep fakes. Subscribe on Apple Podcasts and Spotify. Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with no ads, extended episodes, outtakes, bonus content, a deep discount in our merch store (soon), and more to come. Let’s do this! Knowable – Learn from the world’s best minds, anytime, anywhere, and at your own pace through audio. Get unlimited access to every Knowable audio course right now. Click here to check it out and use code CHANGELOG for 20% off! Featuring:David Kanter – Twitter, GitHubChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Learn more about People’s Speech Get involved with the People’s Speech project MLCube GitHub, including several different examples MLCube Mailing list MLPerf Training Benchmarks MLPerf Training HPC Benchmarks MLPerf Inference Datacenter Benchmarks MLPerf Inference Edge Benchmarks MLPerf Inference Mobile Benchmarks MLCommons on Twitter Something missing or broken? PRs welcome!

American Express is running what is perhaps the largest commercial ML model in the world; a model that automates over 8 billion decisions, ingests data from over $1T in transactions, and generates decisions in mere milliseconds or less globally. Madhurima Khandelwal, head of AMEX AI Labs, joins us for a fascinating discussion about scaling research and building robust and ethical AI-driven financial applications. Join the discussionChangelog++ members get a bonus 2 minutes at the end of this episode and zero ads. Join today!Sponsors:Code-ish by Heroku – A podcast from the team at Heroku, exploring code, technology, tools, tips, and the life of the developer. Check out episode 98 and episode 99 for insights on the ethical and technical sides of deep fakes. Subscribe on Apple Podcasts and Spotify. Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with no ads, extended episodes, outtakes, bonus content, a deep discount in our merch store (soon), and more to come. Let’s do this! 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. LaunchDarkly – Test in production! Deploy code at any time, even if a feature isn’t ready to be released to your users. Wrap code in feature flags to get the safety to test new features and infrastructure in prod without impacting the wrong end users. Featuring:Madhurima Khandelwal – LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: AMEX AI Labs research O’Reilly article about “doing good data science” Something missing or broken? PRs welcome!

Braden Hancock joins Chris to discuss Snorkel Flow and the Snorkel open source project. With Flow, users programmatically label, build, and augment training data to drive a radically faster, more flexible, and higher quality end-to-end AI development and deployment process. Join the discussionChangelog++ members get a bonus 2 minutes at the end of this episode and zero ads. Join today!Sponsors:DigitalOcean – Get apps to market faster. Build, deploy, and scale apps quickly using a simple, fully managed solution. DigitalOcean handles the infrastructure, app runtimes and dependencies, so that you can push code to production in just a few clicks. Try it free with $100 credit at do.co/changelog. Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with no ads, extended episodes, outtakes, bonus content, a deep discount in our merch store (soon), and more to come. Let’s do this! 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. LaunchDarkly – Power experimentation at any scale. Fast and reliable feature management for the modern enterprise. Featuring:Braden Hancock – Twitter, WebsiteChris Benson – Twitter, GitHub, LinkedIn, WebsiteShow Notes: Snorkel AI Snorkel OSS Snorkel Blog Snorkel AI | Twitter Snorkel AI | LinkedIn Snorkel Best of VLDB paper Snorkel Drybell collaboration with Google Jerod recommends Getting Waymo into autonomous driving (Drago Anguelov) Building the world’s most popular data science platform (Peter Wang) Achieving provably beneficial, human-compatible AI (Stuart Russell) Something missing or broken? PRs welcome!