Uploaded June 2023 | Updated September 2026, 2 weeks ago

---

A failed attempt at machine learning for real-time sound design in Pure Data Vanilla.

I've previously shown artificial neurons (youtu.be/PdJG5SFmVaw) and neural networks (youtu.be/VAJeJAr3J7I) in Pd, but here I attempted to take things to the next step and make a cybernetic system that demonstrates machine learning. It went good, not great.

This system has a "target" waveform (what we're trying to produce). The neuron takes in several different waveforms, combines them (with a nonlinearity), and then compares the result to the target waveform, and attempts to adjust accordingly.

While it fails to reproduce the waveform in most cases, the resulting audio of a poorly-designed AI failing might still hold expressive possibilities.

0:00 Intro / Concept
1:35 Single-Neuron Patch Explanation
3:23 The "Learning" Part
5:46 A (Moderate) Success!
7:00 Trying with Multiple Inputs
10:07 Neural Network Failure
12:20 Closing Thoughts, Next Steps

LINKS:
Subscribe: youtube.com/user/SimonHutc/?sub_confirmation=1
Official Website - simonhutchinson.com
bandcamp: simonhutchinson.bandcamp.com/follow_me
facebook: facebook.com/SimonHutchinsonComposer
Buy me a coffee: ko-fi.com/simonhutchinson
Buy my old gear (affiliate link): reverb.grsm.io/simon
Sign up for my mailing list: eepurl.com/hVs7bT

#puredata #machinelearning #artificialintelligence #sounddesign