@elden I don't think it's very popular. I only remember IOhannes mentioning in on Pd's mailing list. It's just a subdomain of Pd's website, deken.puredata.info, and you can search all of deken (Help -> Find externals) in your browser.

@elden Try the Pd website (the deken subdomain) https://deken.puredata.info/search.html?libraries=list-abs&objects=&descriptions=

zexy's [oreceive] is also a dynamic receive. Always worth trying stuff yourself though!

That's rather ambitious indeed. I don't believe you'll be able to display the actual patch. Even if you want to only display knobs and other widgets, you'll have to code this interface yourself and control Pd, or have Pd control those, by sending values for these widgets via OSC.
If I understand what you describe, you want to create a graphical user interface to control a Pd patch, right? If this is so, then what I wrote about holds.
You could try to find some library (it would probably be Python or C++) that creates widgets for OLED displays, and use that together with OSC, but the API you'll use should support OSC communication.

A 200ms is probably a bit too long for what you need. 20ms should be OK for avoiding clicks.
For what you want to do, you probably need two buttons, one for starting and one for early stopping. The second one should first bang a "1, 0 20" message sent to a [line~], then bang a [del 20] object, to delay this bang by 20ms, and the [del 20] should bang a [t b b b] (use as many "b" here as you need) to restart the whole process of playing back a file (including banging the "0, 1 200" message).

@jyg it hasn't been digitally signed, so I guess that's why you get this error. Can't the object be installed with this error? Otherwise you can get the source and compile yourself https://github.com/alexdrymonitis/neuralnet

It's just an Multi-Layer Perceptron (MLP) - a dense feed-forward neural network. Each neuron sends its output to all neurons in the next layer. Each neuron in the next layer multiplies its of its inputs by a weight. The weighted inputs are summed and added to a bias value, then passed through the activation function of the layer (e.g. a sigmoid function to ensure everything remains between 0 and 1 and don't go to +/- infinity) and passed to all the neurons in the layer after that.
It's all in the C code. If you want to learn more about this though (in case you don't know), I recommend the "Neural Networks from Scratch in Python" book, which is where I initially translated Python code to C to create this object.

[neuralnet] does no FFT. You'll have to do all the FFT and IFFT after you get output from [neuralnet]. This object only enables you to create neural networks. What sort of data you'll use and how you'll prepare it is totally up to you.
From what I understand from your post, you should probably store your FFT spectra, and classify them according to the amplitude you mention. Then feed them together with the classes you have created to [neuralnet]. Does this make any sense?

If you are talking about evolution, then it's likely you need something like a recursive neural network (RNN), which [neuralnet] can't create (at least not yet). Unless this evolution you mention can be encapsulated in one snapshot. If it's spectral snapshots with a 256 bin resolution, and you need four of these snapshots to classify your data, then a network with 1024 inputs could worh with [neuralnet].
The MNIST dataset example (example 4) is a classification example. You should follow that to build your network structure (concerning activation functions, loss function, etc.).
With the current versino of the object you can also build autoencoders, which can be sort of good for compressing data. That being said, you could perhaps use an autoencoder and map the values in the latent space. The next version will hopefully include variational autoencoders (working on this), so that could also be an option.
As I don't know the structure of your data though, I don't think I can be of more help right now.

You can also try [neuralnet] which is built for creating (deep) neural networks.