Keynote: Tiny Data Collectors, Vastly (...) & the Land of Tiny Challenges
summary
Survey of small IoT deployments shows concrete experiments: a desktop edge schedules robot-car tasks by battery, CPU and RAM and reduces variance by lowering image resolution; a Raspberry Pi micro-cluster serves phone-like workloads and cuts latency; roadside units use processors smaller than a Pi to warn vehicles. Analysis finds simple statistical filters on-device often replace heavy ML, and an Elixir federated-learning prototype (paper submitted) implements granular model aggregation by context rather than a single global model.
AI-written summary · about
chapters (9)
- 0:0006:12 - Tiny Data collectors
- 6:1311:33 - On the edge
- 11:3416:18 - Vastly distributed systems
- 16:1920:47 - Federated Learning
- 20:4823:24 - Federated Learning Frameworks
- 23:2528:37 - The Land of Tiny Challenges
- 28:3833:41 - Erlang/ Elixir ecosystem
- 33:4237:21 - The Land of Opportunities
- 37:2242:54 - QnA
related talks
31mKeynote: The next big thing in machine learning is tiny
01h 53mTinyML: Machine Learning’s Future is Tiny and Bright
17mKeynote: Beyond the Cloud: Edge Computing
27mWhat’s TinyML good for
57mKeynote: The Demarcation of the Edge of Innovation
11mLightning Talk: Accelerating Experimentation...
46mOpen Hardware Lightning Talks
28mMachine Learning on the Edge