Internal measuring models in trained neural networks for parameter estimation from images

The internal representations of 'learned' knowledge in neural networks are still poorly understood, even for backpropagation networks. The paper discusses a possible interpretation of learned knowledge of a network trained for parameter estimation from images. The outputs of the hidden layer are the internal components of the output parameters. The input-to-hidden weight maps, functioning as a kind of internal measuring model of the parameter components, include statistical features of the training set and seem to have a clear physical and geometrical meaning.<
>