There is another Boston Android Meetup coming your way - 100% virtual with a guest speaker from out of town. The link to the event will be posted closer to event time to avoid trolls.

If you would like to give a talk, please get in touch. The Meetup team asks that you be excellent to each other and to our speakers. The format will have presentations followed immediately by Q&A.

I look forward to seeing you on the Meet.

TALK 1 - Superpower your Android Apps with ML: Android11

Rishit Dagli is our guest for this event. In this session, you get an overview of the tools that power Android apps with Machine Learning. The Model Binding plugin that is new to Android 11 will be discussed along with using pre-trained models with MLKit, especially TensorFlow Hub to run onboard the device in the app. Build high-quality machine learning apps based on your own models or models contributed by the community. Let Rishit show you how easy it is to use custom TF Lite models on Android. The new Neural Network API supports Asymmetric integer weights making model sizes and inferences smaller to open up larger opportunities for network edge ML with demos for these topics.

Rishit is a student and a past TED-X/Ted-Ed speaker. He is an AI on Android enthusiast and a Google Certified Mobile site developer. He has 7 research papers in the field of AI and Robotics and Mathematics and was among the top 10 winners for the Palo Alto Networking Challenge with Google Cloud Platform. He also organizes the communities Kotlin Mumbai and Mozilla Mumbai.

TALK 2 - Practical AI

The second talk for our September Meetup is "Practical A.I." from our very own Elizabeth Mezias. Her presentation will showcase the MLKit APIs from Google that can make iOS and Android apps more engaging and helpful with computer vision that is optimized to run on device. The APIs are built with the same Tensor Flow technology that Rishit will discuss. The example code for text recognition shows you how to write code to use any of the API models: text recognition, face detection, barcode scanning, image labeling, object detection, object tracking, smart reply, text translation, and language identification.

Elizabeth's talk will unveil the latest version of the RoloScan open-source, now migrated to Kotlin and moved from the Firebase APIs to the new MLKit packages.

The Firebase/Java RoloScan source code is available on github. A compiled apk is sold on the Play Store.
https://play.google.com/store/apps/details?id=com.mezcode.demo.roloscan