The problem would be remembering that decision for the next iteration.įor 'learning' to make sense as a concept, you need a goal, and then you need a system complex enough that that goal can be encoded within the system.Īnother way of looking at it might be that a multiple feedback generative patch already is a learning algorithm. Compare S&H to sequence, and if one voltage is higher than the other, do something. I'm thinking a sequence with a parallel LFO/sample and hold. Feed it with a sequence and see how it slowly replicates it and then develop the sequence.įor sure, but a machine learning patch would be cooler. Gis_sweden wrote:A “machine learning module” would be cool. But of course the network could output cv or audio as well. This seems to be the way it usually works in the buzzword bingo setting. When neural nets are used as classifiers there has to be a complexity reduction and a whole lot of information loss between the input and the output. But in general, I think the input typically would be one or more audio signals, or perhaps a bunch of cv signals, and the output might just be a gate signal which classifies all input into two kinds.
I'm sure there must be other applications even though the cowbell recognizer is the only one I can come up with. Then you could build things like a cowbell recognizer: feed it audio, and it outputs a gate whenever it hears the cowbell.
The neural network architecture might be fixed once and for all if that makes it easier. I suppose a neural net module would be feasible if you do the learning offline on a computer and upload the set of weights and biases to the module.
In the modular world what do we have as datasets? Sequences? Something else? How would we take in inputs? Comparators, envelope followers, logic.? Algorithms we probably wouldn't have any problem with. If it's c, how would this work? The way I understand neural networks and machine learning is it learns from a provided dataset, compares inputs with what it's learned, and makes a decision based on some algorithms. B) Musically interesting, but in a different context (like the functioning of a module)?Ĭ) Musically interesting in a patching context?
0 kommentar(er)
