<aside> 💡 Train your own image classifer using transfer learning and ml5.js and apply the model to an interactive p5.js sketch. You can train the model with Teachable Machine or with your own ml5.js code. Feel free to try sound instead of or in addition to images. You may also choose to experiment with a "regression" rather than classification.
</aside>
Screen Recording 2023-09-22 at 9.24.58 AM.mov
I created a simple game module in which players can ‘play’ rock-scissors-paper with the machine but lose all the time. The purpose of this module was to explore the power of technology. AI technology and image recognition are much more advanced than expected, so even individuals can easily create their own models. However, can we confirm that these developments are heading towards humanity’s benefits? I hope this module opens a consideration of whether it is human who plays with machines or machine that ‘will play’ with a human mind.
I trained the Teachable Machine in three groups: Rock, Scissors, and Paper. The background noise sometimes interfered with readings, so simplifying the visual element was important. For this case, I put my hand in front of my black t-shirt and intentionally hid my face to exclude unnecessary noises from influencing the machine’s interpretation.
https://teachablemachine.withgoogle.com/models/bphJCxBHt/
And then, I exported the model and called it in p5.js file below. Using a simple if statement, I created a small interaction chain accordingly to the user’s input.
p5.js page