Google’s Teachable Machine makes it easy to train and deploy ML models

Google's Teachable Machine now makes the ML model training easy. It is an experiment from Google to bring a no-code and low-code approach to training AI models. Anyone with a modern browser and webcam can quickly train a model with no prior knowledge or experience with AI. Teachable Machine is was initially launched in 2017 and got revamped in 2019 with additional capabilities, including saving the model to Google Drive and exporting it to other applications.

The magic behind Teachable Machine is based on a popular deep learning technique called transfer learning. Most of the neural network architecture of a fully trained model is retained while replacing a minor part of it based on the data. Teachable Machine supports models based on images, sounds, and poses. The browser simply relies on your machine's inbuilt microphone to capture 10 seconds of audio samples for sound.

You can train models that can detect your hand movements and body poses - all from the webcam. The best part of Teachable Machine is the ability to export the model to various environments and applications. Google aims to introduce Google Colab Notebook to tweak the code, enabling power users and developers to extend it further.