Google’s Teachable Machine is a pretty exciting concept. If you’re interested in Artificial intelligence but you’ve never dared wander into that realm because all that sciency stuff is… well, sciency, then Google’s Teachable Machine description will provide relief when you read it:
A fast, easy way to create machine learning models for your sites, apps, and more – no expertise or coding required.
Google Teachable Machine
So how does Teachable Machine work?
There are 3 easy steps you have to follow:
- Gather – Gather and group your examples into classes, or categories, that you want the computer to learn.
- Train – Train your model, then instantly test it out to see whether it can correctly classify new examples.
- Export – Export your model for your projects: sites, apps, and more. You can download your model or host it online for free.
The Teachable Machine website states that you can make models based on 3 types of data sets; Sounds, Images and Poses. The website also has tutorials to teach users how to get the hang of using the Teachable Machine.
Outside of simple playful AI and ML solutions, Teachable Machine can be used to solve real-world problems. One such use case was suggested in a blog post by Zimbabwean Babusi Nyoni:
An example that immediately jumps to mind is the field of dermatology and the opportunities Teachable Machine presents for medical practitioners to curate their own data and train much-needed models to identify potentially fatal skin conditions without supervision.
Babusi Nyoni
The greatest attribute of Teachable Machine is probably the fact that it shows people that AI and Machine Learning, whilst “sciency” are not necessarily concepts that are out of this world and the solutions for AI can very much be grounded in our day to day reality.
