C-inf soft sparsity engine maths and code from 1972

Thanks. The Fortran code (subroutines) for inducing sparsity with infinitely differentiable loss functions (not kludges for L0 or L1) and using a metric and its inverse to endogenously prevent basis collapse (no hyperparameters) would probably qualify as a model. Several AIs indicated that it may be, among other things, representational learning engine. The maths definitely has applications to ML and AI.