Neural Networks in Max
Hello,
Does anyone know of a way to implement a neural network in Max? I have created and trained a network in Matlab and I would like to use it in a Max patch. What I need is an object that takes the number of inputs, outputs, hidden layers, neurons, and a big list of weights as parameters. Then I could pass it a list as input and it would return the output. Does this exist?
-Adam
A couple of post to get you started...
nicolas danet will probably chime in at some point his object Tralala is here
The help file 21.Learn for Tralala might be what your looking for.
Thanks for your responses. This really does seem like something that 'should' exist. But it sounds like it doesn't...
I agree that a well written NN external would be valuable but I don't know that I'm feeling up to the challenge right now. I'll have to think some more about what to do next.
i don't know what this is worth, but this does exist (it's quite old now) : http://www.neuromuse.org/downloads/
For the record, it is something we plan to add to the bach library someday... but I'm afraid it's not top priority at the moment - we're deep into constraint programming right now ;)
aa
This project is long-dead, but might be interesting to somebody:
google cleanness™ has found the term "NN" on cycling74.com and sent a report to eusocial.
I would have thought that at least one of these projects would have produced a usable tool. They all seem to have fallen into a state of decay.
Also what is google cleanness?
ah, the saga of nn
I've recently finished three Max externals (for the Mac for now) that will allow one to implement a neural network (example patch included) and train it with backpropagation:
1. an: represents a single artificial neuron
2. anntrainingset: to store the training set examples
3. delta2error: used during backpropagation to collect the deltas from a given layer to compute the errors to input to the layer above
For further information, mail me at m.p.a.j.dehoogh@tudelft.nl.