Daniel and Chris have a fascinating discussion with Anna Goldie and Azalia Mirhoseini from Google Brain about the use of reinforcement learning for chip floor planning - or placement - in which many new designs are generated, and then evaluated, to find an optimal component layout. Anna and Azalia also describe the use of graph convolutional neural networks in their approach.Sponsors:Linode – Our cloud of choice and the home of Changelog.com. Deploy a fast, efficient, native SSD cloud server for only $5/month. Get 4 months free using the code changelog2019 OR changelog2020. To learn more and get started head to linode.com/changelog. AI Classroom – An immersive, 3 day virtual training in AI with Practical AI co-host Daniel Whitenack. Get 10% off using the code PRACTICALAI10. To learn more and purchase tickets go to datadan.io. 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:Anna Goldie – GitHub, LinkedIn, XAzalia Mirhoseini – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Their research paperGoogle BrainGoogle is using AI to design chips that will accelerate AI | MIT Technology ReviewPractical AI episode #47: GANs, RL, and transfer learning oh my!Upcoming Events: Register for upcoming webinars here!