Search code examples
neural-networklasagne

Neural network: "InverseLayer"

I play around with neural networks. I understand how convolutional layers, fully connected layers and many other things work. I also know what a gradient is and how such a network is trained.

The framework lasagne contains a layer called InverseLayer.

The InverseLayer class performs inverse operations for a single layer of a neural network by applying the partial derivative of the layer to be inverted with respect to its input.

I do not know what this means or when i should use this layer in general. Or what is the idea behind of inverting the partial derivative?

Thank you very much

Solution

  • The InversLayer is needed when creating the Deconvolution Network. For more details take a look here: http://cvlab.postech.ac.kr/research/deconvnet/