Improving Neural Network-Based Multi-Label Classification With Pattern Loss Penalties

Improving Neural Network-Based Multi-Label Classification With Pattern Loss Penalties

This research work introduces two novel loss functions, pattern-loss (POL) and label similarity-based instance modeling (LSIM), for improving the performance of multi-label classification using artificial neural network-based techniques. These loss functions incorporate additional optimization const...

Full description

Bibliographic Details
Main Authors: Worawith Sangkatip, Phatthanaphong Chomphuwiset, Kaveepoj Bunluewong, Sakorn Mekruksavanich, Emmanuel Okafor, Olarik Surinta
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Multi-label classification
label correlation
label-specific features
deep neural network
loss functions
Online Access:https://ieeexplore.ieee.org/document/10495049/

Internet

https://ieeexplore.ieee.org/document/10495049/

Similar Items