Paper ID: 2209.08422

Computed Decision Weights and a New Learning Algorithm for Neural Classifiers

Eugene Wong

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.

Submitted: Sep 17, 2022