Machine Learning on the Edge

on YouTube ↗09m

" summary

Explains how to run models on phones using ML Kit with optional Firebase integration removed recently so projects no longer must be Firebase apps, and how TensorFlow Lite and AutoML Vision Edge provide mobile models. Shows base APIs (barcode, text, labels) returning multiple guesses — example image yields three labels like television computer musical instrument — and how to bundle a custom TFLite model for higher accuracy, enable cloud vs on device fallback, and build features such as Snapchat‑style face filters.

AI-written summary · about

" chapters (4)

1. 0:00Start
2. 2:12Traditional ML approach
3. 5:26Add dependencies
4. 5:38MLKit base apis Image detection

" related talks

• 36mMachine Learning for Mobile DevelopersLaura Morinigo · Mobilization 8
• 24mML Kit: Machine learning for mobile developersSachin Kotwani, Isabella Chen · Firebase Summit 2018
• 39mMachine Learning on Android DemystifiedTatyana Casino · droidcon SF 2019
• 14mDo you want an easy way to add Machine Learning into your app?Sandra Dupré · Android Makers 2019
• 29mPushing Machine Learning into your app When TensorFlow and MLKit rule the worldSandra Dupré · DevFest Nantes 2018
• 07mMachine Learning on the EdgeSangeetha KP · React Summit Remote Edition 2020
• 29mFirebase MLKit — AI in Android Town!!Sweety Bertilla Francis Xavier · Android Summit 2019
• 04mTop 5 reasons to add ML Kit to your Android or iOS appSachin Kotwani · Firebase Summit 2018