In this paper we consider the possibility of computing rather than training the decision layer weights of a neural classifier. Such a possibility arises in two way, from making an appropriate choice of loss function and by solving a problem of constrained optimization. The latter formulation leads to a promising new learning process for pre-decision weights with both simplicity and efficacy.
@article{arxiv.2209.08422,
title = {Computed Decision Weights and a New Learning Algorithm for Neural Classifiers},
author = {Eugene Wong},
journal= {arXiv preprint arXiv:2209.08422},
year = {2022}
}