How to Invert a Neural Network
13 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
Blake Van Winkle
il 13 Gen 2020
Modificato: Taimoor Tariq
il 5 Feb 2020
I have trained a model with states as inputs and an output of the cumulative distribution function (CDF) of any specific state, which is designed to mitiage any confusion in the network if multiple points have the same probability. I would like to flip the model instead of training an entirely new model because of the computational requirements and the probability that they won't agree with each other. Does anyone know how to do this with Matlab's Deep Learning Toolbox?
Trained: CDF = NN(X)
Invert: X = NN(CDF)
0 Commenti
Risposta accettata
Taimoor Tariq
il 3 Feb 2020
Maybe this will help.
2 Commenti
Taimoor Tariq
il 5 Feb 2020
Modificato: Taimoor Tariq
il 5 Feb 2020
The code is compatible with Image input CNNs defined using matconvnet. Now if you have a Image input model trained on the Deep Learning Toolbox, you could probably export it to matconvnet using ONNX and then use the code. However, I think in your case In dont think you are using images as input, you would probably have to tweak the code a lot, or maybe write your own.
Più risposte (1)
Srivardhan Gadila
il 17 Gen 2020
If your network is a fully connected, has no non-linearities(like activations)/non-linear layers and has invertible wieght matrices for all your layers, then only you can invert your trained network by using the inverted weight matrices & bias vectors.
3 Commenti
John D'Errico
il 22 Gen 2020
Note that any such inverse as you desire need not be unique, or even terribly well posed, just as would be true for any inverse of a general nonlinear relationship.
Vedere anche
Categorie
Scopri di più su Image Data Workflows in Help Center e File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!