Semi-Supervised Learning Algorithm Based on AFS Theory and LogitBoost Algorithm

There are a wide variety of classification problems in the world, so the classification task has always been a fundamental and important machine learning problem. However, many scholars have focused on the accuracy and training speed of classification models, while neglecting an important factor of classifier models: interpretability. In many cases, it is extremely difficult to collect labeled data, so the use of both labeled and unlabeled data to train classifiers that generate better semi-supervised learning is also the focus of many scholars. For the above reasons, this paper proposes a new classifier, which is based on the axiomatic fuzzy set(AFS) theory. It not only realizes the interpretability of the fuzzy theory, but also uses the LogitBoost algorithm to verify the inconsistency of the axiomatic fuzzy set theory.