The ml5.js community page is dedicated to highlighting artists, technologists, makers, activists, thinkers, tinkerers, researchers, scientists, designers, students, and anyone/everyone who are working in and around machine learning in thoughtful ways. Many of these posts not only showcase what is possible with ml5.js but also what can be done when applying machine learning methodologies and technologies more broadly. Special emphasis is given to projects that highlight ethical and critical engagement with technology and/or are simply delightful.
If you are interested to share your work, highlight an interesting article/video, or get in touch, we'd love to hear from you. Get in touch via Google Forms here: ml5js.org Community Submission Form.
This playlist provides an introduction to developing creative coding projects with machine learning. The theory and application of machine learning algorithms is demonstrated in JavaScript using the p5.js and ml5.js libraries.
→ visit
A motorcycle game generated by your voices, built with Pitch Detection model in ml5.js.
→ visit
You can play whack a mole with your nose👃. It's a physical game on the web developed with PoseNet.
→ visit
The AI Now 2019 Symposium provided behind-the-scenes insights from those at the frontlines of the growing pushback against harmful AI. The videos of the talks are available to watch online.
→ visit
Geography of Hidden Faces uses ml5's face-api to explore how of facial recognition algorithms behave when applied to aerial imagery.
→ visit
Google's new Teachable Machine 2.0 is released! Train your own machine learning models in the browser with this beautifully designed tool.
→ visit
An interactive type projection/website that mashes the simple body tracking provided by Posenet with particle movement based on the Reynolds Flocking algorithm. When there is no one in view, the installation renders an ambient flow of boids. But when PoseNet detects a person in view, the particles become letterforms that can be distorted with your hands.
→ visit
Play the rhythm with your hands 🤚, powered by PoseNet. Connecting dance movements to music is not a special idea, but using PoseNet with webcam can bring this experience to anyone with a laptop. Also, the visual feedback of "Body Beat" can enhance to tangibility of music and sounds. For example, a ball is created between player's hands and the size of it is mapped to the volume of the sounds.
→ visit
The "Amazing Augmented Tagger Machine" is a hybrid of a custom-made piece of software and an interactive installation, based on a deep convolution neural network, trained on a data set of ~1,000 annotated street tag images from Germany.
→ visit
A real-time pose estimation in the browser using ml5.js, PoseNet model and fancy 3D objects. The project is based on the artist’s personal interest in tracking systems. Exploring the possibilities of facial and body recognition, playful body AR filters are just the shy reminders of how precisely machines see us moving.
→ visit
Airi Flies is an interactive game played using your voice. To start the game say PLAY. Say PEW to make Airi fly. If you lose more than 8 points or hit an obstacle, you lose. This project was created to encourage people to get out of their comfort zone and feel more confident about themselves regardless of what they do and what they look or sound like.
→ visit
Jim Schmitz has developed a new method of applying style transfers to 360 photos and video. (Not using ml5.js yet but we hope someday!)
→ visit
Let’s Read a story is a study on Aesop Fables and the possibility of exploring the connections between different characters and ideas from the original fables in a new and fun way using recently available machine learning tools.
→ visit
A game by Lillian Ritchie that prompts players to maintain the natural balance of ocean life. Steer with your nose!
→ visit
Humans of AI is an online exhibition comprised of three works based on the COCO (Common Objects in Context) image dataset.
→ visit
In conversation with ITP SIRs Nikita Huggins & Ayodamola Okunseinde
→ visit
In Conversation with ITP SIR Stefania Druga
→ visit
Alias is a teachable “parasite” that is designed to give users more control over their smart assistants, both when it comes to customisation and privacy.
→ visit
Written in 2018 by Mimi Onuoha and Mother Cyborg (Diana Nucera), A People’s Guide to AI is a comprehensive beginner's guide to understanding AI and other data-driven tech.
→ visit
Blog post on the origins of ml5.js
→ visit
In July 2018 a group of artists, designers and creatives worked for three days on the creation of new methods of authentication, using machine learning
→ visit
Recomposing images in the style of other images.
→ visit
Simple example based on Google's Teachable Machines Project.
→ visit
An experimental web text editor that runs a LSTM model while you write to suggest new lines.
→ visit
"Beat the Traffic" is an AI based mini game where you create a mobility wonderland in cities around the world. Players can globally enchant traffic jams at iconic locations and turn them into nicer things like unicorns, rainbows and driving trees.
→ visit