Uploaded March 2023 | Updated September 2026, 2 weeks ago
Talking through the concept of an artificial neuron, the fundamental component of artificial intelligence and machine learning, from an audio perspective.
I've made a few videos recently with "artificial neurons" including in Pure Data (youtu.be/PdJG5SFmVaw & youtu.be/VAJeJAr3J7I) and in Eurorack (youtu.be/NeQYA4SIkGw), and, in this video, I discuss the ideas here in more detail, specifically how an artificial neuron is just a nonlinear mixer.
An artificial neuron takes in multiple inputs, weights them, and then transforms the sum of them using an "activation function", which is just a nonlinear transformation (of some variety).
Of course just making a single neuron does not mean you've made an artificial intelligence or a program capable of "deep learning", but understanding these fundamental building blocks can be a great first step in demystifying the growing number of machine learning programs in the 21st Century.
More music and sound design with artificial neurons: youtube.com/playlist?list=PL7w4cOVVxL6GojicLv-6sTL-l63pVSPQP
0:00 Why Neurons?
1:04 Defining Artificial Neurons
1:30 Activation Functions
2:22 Again, why?
3:01 Audio Nonlinearity
3:29 Nonlinear Circuits Neuron in VCV Rack
5:43 Mixing Multiple LFOs
6:13 Moving to Audio Rate
7:22 Comparing to Linear Mixing
8:12 Acknowledging Weighting
8:34 Different waveforms
9:44 In Pure Data, Reaktor, Max/MSP, Kyma, and Eurorack
10:37 Different Nonlinear Transformations
10:51 Machine Learning?
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
#vcvrack #machinelearning #experimentalmusic #soundsynthesis
Talking through the concept of an artificial neuron, the fundamental component of artificial intelligence and machine learning, from an audio perspective.
I've made a few videos recently with "artificial neurons" including in Pure Data (youtu.be/PdJG5SFmVaw & youtu.be/VAJeJAr3J7I) and in Eurorack (youtu.be/NeQYA4SIkGw), and, in this video, I discuss the ideas here in more detail, specifically how an artificial neuron is just a nonlinear mixer.
An artificial neuron takes in multiple inputs, weights them, and then transforms the sum of them using an "activation function", which is just a nonlinear transformation (of some variety).
Of course just making a single neuron does not mean you've made an artificial intelligence or a program capable of "deep learning", but understanding these fundamental building blocks can be a great first step in demystifying the growing number of machine learning programs in the 21st Century.
More music and sound design with artificial neurons: youtube.com/playlist?list=PL7w4cOVVxL6GojicLv-6sTL-l63pVSPQP
0:00 Why Neurons?
1:04 Defining Artificial Neurons
1:30 Activation Functions
2:22 Again, why?
3:01 Audio Nonlinearity
3:29 Nonlinear Circuits Neuron in VCV Rack
5:43 Mixing Multiple LFOs
6:13 Moving to Audio Rate
7:22 Comparing to Linear Mixing
8:12 Acknowledging Weighting
8:34 Different waveforms
9:44 In Pure Data, Reaktor, Max/MSP, Kyma, and Eurorack
10:37 Different Nonlinear Transformations
10:51 Machine Learning?
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
#vcvrack #machinelearning #experimentalmusic #soundsynthesis
