What does it take to implement machine learning in your app? In this talk, Tatyana Casino will suggest different ways to approach this. There will be comparisons between cloud-based services and local (on-device) machine learning, focusing mostly on the latter. On-device predictions are happening strictly on a mobile device, giving you the benefit of keeping the users' data private and not depending on the network connection. Features like Google Lens Suggestions, Call Screening, and Live Caption are all leveraging on-device ML. However, the ML models should be prepared and optimized for efficiency and performance on mobile. For actual implementation, Tatyana will look into how to use TensorFlow Lite SDK for pose estimation. Then there will be coverage of Firebase MLKit Base APIs and using custom models with MLKit. Code examples will be in Kotlin. After attending this talk, you will understand the capabilities and limitations of each of these frameworks. You will have a good idea of where to start, what is necessary to implement your ML idea in your app, and potential issues to be aware of.