1. Pick one of the models above (PoseNet, HandPose, UNET, BodyPix, CoCoSSD) and following the examples and ml5.js documentation experiment with controlling elements of a p5.js sketch (color, geometry, sound, text) with the output of the model. (You may also choose a ml5.js model not covered here if you like!)

[https://editor.p5js.org/sirui/sketches/HINCRkH-J](https://prod-files-secure.s3.us-west-2.amazonaws.com/0f6320a2-b9a7-4f1a-b962-0350eab3fe4c/bce3c3fc-fb02-4310-9a44-8a7f8b1b2bf9/Untitled.mp4)

https://editor.p5js.org/sirui/sketches/HINCRkH-J

1. Considering the Model and Data Biography reflect on the the following questions:

• What questions do you still have about the model and the associated data? Are there elements you would propose including in the biography?

How do model developers and data collectors collaborate? Do model developers have the power to modify the dataset for better training?

• How does understanding the provenance of the model and its data inform your creative process?

I noticed that for the BodyPix model, the training data contains two parts: images in the dataset and simulated data. If we did not research into the model biography, we would not know that the dataset is mixed. Therefore, I would consider listing down the reference and data source for my future projects in a more rigorous manner.