Work

One-Step Abductive Multi-Target Learning with Diverse Noisy Label Samples

Year: 2021

Type: preprint

Abstract: One-step abductive multi-target learning (OSAMTL) was proposed to handle complex noisy labels. In this paper, giving definition of diverse noisy label samples (DNLS), we propose one-step abductive multi-target learning with DNLS (OSAMTL-DNLS) to expand the methodology of original OSAMTL to better handle complex noisy labels.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2201.07933

Author: Yang, Yongquan

Language: English

Topic: Machine Learning and Data Classification

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4226494878

Cites:

Cited by: 1

Related to: 10