Google's Teachable Machine
Teachable Machine is a service by Google that allows training different machine learning models without programming a line of code. With some coding, we can integrate the model into our app.
Last updated
Was this helpful?
Teachable Machine is a service by Google that allows training different machine learning models without programming a line of code. With some coding, we can integrate the model into our app.
Last updated
Was this helpful?
Google's Teachable Machine (GTM) runs fully in the web-browser. This means you can directly click on the link below to start training your model:
GMT currently supports 3 different use cases. You can train models to classify images, sound or poses. For the image and pose classification, you need a webcam to create the training images and to run the model live in the browser. For the audio model, you need a microphone to record training data and apply the model to new sound input afterwards.
In this course, we look at the examples of image and sound classification in more detail. We'll learn how we can train a new model for both tasks and how we can export the model to integrate it into our app. If you want to try the classification of different poses, feel free to try training a model yourself. The concepts to integrate the model into your app are very similar.
GTM is based on , which is a lightweight web-version of the popular machine learning framework based on JavaScript. TensorFlow is originally developed by Google and is provided as open-source software for anyone to use.
Since GTM is based on JavaScript, it integrates well with other tools and libraries we use in this course. These include Glitch and p5.js. We can also use GTM models (i.e. TensorFlow.js models) with ml5.js, a machine learning library we'll introduce .
One of the use cases supported by GTM is .
[1] Michelle Carney, Barron Webster, Irene Alvarado, Kyle Phillips, Noura Howell, Jordan Griffith, Jonas Jongejan, Amit Pitaru, and Alexander Chen. 2020. Teachable Machine: Approachable Web-Based Tool for Exploring Machine Learning Classification. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems (CHI EA '20). Association for Computing Machinery, New York, NY, USA, 1–8. DOI:
