<aside> 📖
https://github.com/ml5js/Intro-ML-Arts-IMA-F24/tree/main/05-neural-networks#ml5js-project-due-october-17
</aside>
<aside> 📖
Watch Machine Learning for Human Creative Practice by Dr. Rebecca Fiebrink at Eyeo 2018. Reflect on the question:
Write a response to this question and outline an initial idea for your project. Do you plan to build on a previous assignment or start something new? This can be a short post— just a paragraph response and a sentence or two about your idea! Post a link on the ml5.js Project Wiki page.
</aside>
NOTES FROM THE SOURCEFinal Thoughts:
This talk was quite eye-opening. It made me realise how you can approach a problem from a different viewpoints. I feel like I have been locked into the more technical point of view up until now trying to find the most optimal solution to a specific problem, while a more artistic person would look at ML as a medium, which they work together with to explore and find something interesting in. I believe the latter stance is great for exploring new ways of how a tool could be utilised, but then in the commercial and business space you need to make that tool reliable.
I believe it is a great medium for experimentation and exploration of a design space; a new approach we can put in our design-toolkit.
<aside> 📖
Develop a p5.js sketch with ml5.js, using one or more of the models we’ve covered in the first half of the semester.
For this assignment I would like to create a proof-of-concept instrument using hand pose. The idea is to have 4 different looping sound files mapped to the users index-, middle-, ring- and pinky fingers. When the user touches any of the above mentioned fingers to their thumbs, the system records that location, and measures the displacement with which we will be able to distort the sound on two auditory dimensions (pitch and volume for example). You could think of it being quite similar to playing a guitar where you can pitch-bend a note when you push the string up.
First I created a small outline for myself to follow in the coding process. This looked something like this: