Elevator Pitch
Want to get started with machine learning but don’t wanna learn Python? OR are you already doing machine learning but don’t know about On-Device ML? If any of the answers are yes then join me to learn more about TensorFlow.js, a library to run client-side ML model using JavaScript.
Description
Running machine learning programs is entirely on client-side. The browser unlocks new opportunities, like interactive ML! If you’re a Javascript developer who’s new to ML, or want to try ML then TensorFlow.js is a great way to begin your journey. TensorFlow.js is an open-source library to define, train, and run machine learning models entirely on the browser, using low-level JavaScript linear algebra library or the high-level layers API. This talk will cover the core concepts of TensorFlow.js with a live demo of an image classifier that you will train on the fly to make prediction through the webcam.
Notes
For Javascript developer who’s new to ML, TensorFlow.js is a great way to begin learning. Or, for an ML developer who’s new to Javascript, TensorFlow.js will make it easy to start with. Developers can use flexible and intuitive APIs to build and train models using high-level APIs and also Retrain pre-existing ML models using sensor data connected to the browser, or other client-side data.
Being a Google MLCC facilitator, I’ve trained more than 400 people about TensorFlow and applying it to real life use-cases. This talk follows the same pattern, in the first half we’ll cover the basics of TensorFlow.js and then we’ll see how we can apply it to a real-life problem like text recognition or object detection with a live demo.