This workshop is completely virtual. The Zoom link is below: Zoom link for the workshop

Recent developments in sensing, sensor algorithms, miniaturized computing, and improved infrastructure are seeing the deployment of learning algorithms on mobile and edge systems. Most future sensing algorithms as well as data analytics will require sophisticated learning algorithms to process and analyze data from the mobile devices. However, this requires mobile systems developers to learn and understand various machine learning algorithms to deploy them, which is challenging. This workshop is interested in developments in algorithms and systems that lower the barrier to deploying learning algorithms on the mobile/edge.

SEMI will bring together top experts in these respective streams to present their latest innovations that address some of these challenges in deploying learning on mobile systems. Topics of interest include, but not limited to:

• Edge abstractions for deep learning
• Federated mobile and edge learning
• Systems support for edge learning
• Simplifying edge/mobile data analytics
• Edge-enabled privacy
• Validation and debugging of edge intelligence
• Emerging applications for edge intelligence
• Mobile systems support for intelligence
• Mobile Backend as a service
• Video analytics on the edge
• System design for edge intelligence
• Distributed and decentralized edge intelligence
• Timeliness of edge intelligence
• Data collection reports for edge intelligence
• Mobile and edge inference
• Energy/Performance challenges in edge intelligence

SEMI invites submission of original work not previously published, or under review at another conference or journal. Accepted papers will be published by ACM.