I recently gave the keynote talk at the IEEE Annual Computing and Communication workshop and conference CCWC-2022 on OnDevice machine learning for mobile and web.

The compute demand for machine learning solutions is exponentially increasing as AI is becoming more ubiquitous in our daily lives. Traditionally, ML models only ran on powerful servers in the Cloud. On-device Machine Learning is when you perform inference with models directly on a device (e.g. in a mobile app or web browser). The ML model processes input data—like images, text, or audio—on device rather than sending that data to a server and doing the processing there. On Device ML has many benefits over traditional cloud AI, such as reduced compute cost, lower latency, and preserving privacy. Google provides easy-to-use turn-key solutions for running ML algorithms on devices for mobile and web. In this talk, we cover how to use and integrate on-device ML models in your app and deploy it in production.