all AI news
Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression. (arXiv:2206.11049v1 [cs.SD])
June 23, 2022, 1:10 a.m. | Meishu Song, Zijiang Yang, Andreas Triantafyllopoulos, Xin Jing, Vincent Karas, Xie Jiangjian, Zixing Zhang, Yamamoto Yoshiharu, Bjoern W. Schuller
cs.LG updates on arXiv.org arxiv.org
We propose a novel Dynamic Restrained Uncertainty Weighting Loss to
experimentally handle the problem of balancing the contributions of multiple
tasks on the ICML ExVo 2022 Challenge. The multitask aims to recognize
expressed emotions and demographic traits from vocal bursts jointly. Our
strategy combines the advantages of Uncertainty Weight and Dynamic Weight
Average, by extending weights with a restraint term to make the learning
process more explainable. We use a lightweight multi-exit CNN architecture to
implement our proposed loss approach. …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Machine Learning Engineer - Sr. Consultant level
@ Visa | Bellevue, WA, United States