How to Invert a Neural Network
11 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Blake Van Winkle
el 13 de En. de 2020
Editada: Taimoor Tariq
el 5 de Feb. de 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 comentarios
Respuesta aceptada
Taimoor Tariq
el 3 de Feb. de 2020
Maybe this will help.
2 comentarios
Taimoor Tariq
el 5 de Feb. de 2020
Editada: Taimoor Tariq
el 5 de Feb. de 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.
Más respuestas (1)
Srivardhan Gadila
el 17 de En. de 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 comentarios
John D'Errico
el 22 de En. de 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.
Ver también
Categorías
Más información sobre Image Data Workflows en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!