• [x] Watch Machine Learning for Human Creative Practice by Dr. Rebecca Fiebrink at Eyeo 2018. Write a response to the following question posed by Dr. Fiebrink:
  • How can machine learning support people's existing creative practices? Expand people's creative capabilities?
• [x] Create your own p5.js sketch that trains a model with real-time interactive data. This can be a prototype of a project idea or a simple exercise where you run this week's code examples with your own data. Here are some exercise suggestions:
• Try to invent more elegant and intuitive interaction for collecting real-time data beyond pressing keys.
• What other real-time inputs might you consider beyond mouse position, image pixels, or face/pose/hand tracking? Could you use real-time sensor data?
• What other real-time outputs might you consider beyond text? Could the output be sound/color modulation? Could there be multiple outputs like R, G, B values? Could the output be a physical computing device?
• Improve the the sketch we built in class:
  • Can you add more classification categories?
  • Can you create an interface for training and showing the results of model's prediction?
  • Can you turn this into a regression model?
• Experiment with the inclusion of convolutional layers for image classification.
• [x] Document your response to the readings as well as your p5.js sketch in a blog post and add a link to the post and your p5.js sketch on the Assignment 5 Wiki page. In your blog post, include visual documentation such as a recorded screen capture / video / GIFs of your sketch.

Video & Notes: Watch Machine Learning for Human Creative Practice by Dr. Rebecca Fiebrink

• How can machine learning support people's existing creative practices? Expand people's creative capabilities?

One of the most exciting points Dr. Rebecca Fiebrink made is how machine learning can be made accessible to everyday people, not just experts or those with advanced degrees. Her focus is on bringing machine learning into creative spaces, helping musicians, artists, and other creators use these tools to enhance their practice. The idea that machine learning isn’t just for engineers or researchers but can be integrated into artistic work is really eye-opening. It shifts machine learning from something distant and technical to something that can enhance people’s creative capabilities in ways they couldn’t achieve on their own.

One of her examples that really resonated with me is how musicians can use machine learning to play sounds they physically can’t perform. This was mind-blowing to me, especially since my father is a musician, and I’ve grown up watching musicians dedicate years to perfecting their craft. Traditionally, there’s a limit to what someone can do with an instrument based on their skill or the instrument's physical constraints. But with machine learning, musicians can go beyond their limits whether it’s playing a note they’re not able to hit yet or even creating entirely new, innovative sounds. (My father would not agree with this though, he is a strong beliver true music is only through physical instruments and practice). It’s inspiring to think how machine learning doesn’t replace the artist but acts as a tool to expand what’s possible, making it a powerful way to push creative practices forward.

Create your own p5.js sketch that trains a model with real-time interactive data.

https://editor.p5js.org/ml5/sketches/rR51vvi-u

• I was very inspired by this Neural Network Training Model, I wanted to incorporate something that used buttons to gather data.

Step 1:

I started by follow a few tutorial to see what worked best for me. I used the https://thecodingtrain.com/tracks/ml5js-beginners-guide/ml5/6-train-your-own-neural-network/1-train-the-model and https://natureofcode.com/neural-networks/. And I made sure to emphasize follow https://docs.ml5js.org/#/reference/neural-network in case anything was outdated.

Attempt #1: Following the Neural Network tutorial on Nature of Code… but then options wasn’t working so I attempted the Ml5.js tutorial instead.