LAUSR

Output Regularization With Cluster-Based Soft Targets.

Sign Up to like & get
recommendations!
2 Published in 2023 at "IEEE transactions on neural networks and learning systems"

DOI: 10.1109/tnnls.2023.3262267

Abstract: While supervised learning of over-parameterized neural networks achieved state-of-the-art performance in image classification, it tends to over-fit the labeled training samples to give inferior generalization ability. Output regularization deals with over-fitting by using soft targets… read more here.

Keywords: soft targets; cluster based; output regularization;