We highlight a formal and substantial analogy between machine learning (ML)
algorithms and discrete dynamical systems (DDS) in relaxation form. The
analogy offers a transparent interpretation of the weights in terms of physical
information-propagation processes and identifies the model function of the forward
ML step with the local attractor of the corresponding discrete dynamics. Besides
improving the explainability of current ML applications, this analogy may also
facilitate the development of a new class ML algorithms with a reduced number of
weights.
Keywords
machine learning, partial differential equations, discrete
dynamical systems