This video was recorded at Code BEAM America 2021 - https://codesync.global/conferences/code-beam-sf-2021/ Machine learning, IoT and Erlang: is this the right mix for reliable federated learning? | Anna-Lito Michala - Assistant Professor in Understandable Autonomous Systems at the School of Computing Science, University of Glasgow ABSTRACT Edge computing and has ground-breaking potential to impact in IoT. Porting Machine Learning capabilities to the IoT device is highly desirable to reduce cloud dependency. Attempts to standardise IoT stacks have not yet gained significant acceptance due to introducing the issues of large incoming data flows, trust, privacy and security, and these are prohibitive for many scenarios. New resilient IoT stacks are necessary to address the problems at the source. That is to enable federated de-centralised solutions, and to maintain accuracy, low computational and power consumption. OBJECTIVE Bounce the idea of the wall and get feedback from the community. Identify other projects working in this domain and explore collaborations. AUDIENCE Anyone working on Embedded systems using Erlang with a keen interest on supporting data driven decision support. • Timecodes 00:00 - 07:01 - IoT, Machine Learning & Edge computing 07:02 - 09:29 - Where Does Erlang/ Elixir fit in? 09:30 - 18:01 - A Use case 18:02 - 20:35 - If We Have Nx, What Else do we Need? 20:36 - 30:22 - QnA • Follow us on social: Twitter: https://twitter.com/CodeBEAMio LinkedIn: https://www.linkedin.com/company/27159258 • Looking for a unique learning experience? Attend the next Code Sync conference near you! See what's coming up at: https://codesync.global • SUBSCRIBE TO OUR CHANNEL https://www.youtube.com/channel/UC47eUBNO8KBH_V8AfowOWOw See what's coming up at: https://codesync.global