A singular Riemannian geometry approach to deep neural networks II. Reconstruction of 1-D equivalence classes

Alessandro Benfenati, Alessio Marta

Abstract: Highlights•The equivalence classes are sets of points that are mapped in the same way by the Neural Network.•We reconstruct equivalence classes of a given label in the NN input manifold.•We develop a strategy to step from an equivalence class to another in input manifold.•We apply the developed algorithms to thermodynamics and classification problems.