Learn More
The internal representations of 'learned' knowledge in neural networks are stili poorly understood. even for backpropagation networks. This paper discusses a possible interpretation of the leamed 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(More)
A statistical model, describing noise-disturbed invariants extracted from a surface patch of a range image, has been developed and applied to region based pose estimation and classification of 3D quadrics. The Mahalanobis distance , which yields the same results as a Baysian classi-fier, is used for the classification of the surface patches. The results,(More)
  • 1