Results 91 to 100 of about 3,537 (211)

Survey on Multi-Task Learning in Smart Transportation

IEEE Access
Artificial Intelligence (AI) has been widely adopted in numerous fields and enabled various smart systems because of its strong ability to perform tasks, including prediction, event detection, and status estimation, among others.
Mohammed Alzahrani, Qianlong Wang, Weixian Liao, Xuhui Chen, Wei Yu   +4 more
doaj   +1 more source

Automated Multi-task Learning [PDF]

, 2017
Multi-task learning (MTL) has recently contributed to learning better representations in service of various natural language (NLP) tasks. MTL aims at improving the performance of a primary task by jointly training on a secondary task.
Liang, Davis
core  

MTL-Light: An Explainable Chained Multi-Task Learning Framework for Rapid Daylighting Performance Prediction in Office Units

Buildings
Accurate evaluation of indoor daylighting performance is essential for improving visual comfort and reducing lighting energy use in office buildings. However, simulation-based daylighting analysis is often too time-consuming to support rapid comparison ...
Gaoyang Liu, Yuting Chen, Yue Zeng
doaj   +1 more source

AoE-MTL: Gate-Free Expert Selection for Efficient Multi-Task Learning

Multi-gate Mixture-of-Experts (MMoE) architectures use task-specific gating networks for expert selection, but these gates add parameters, tuning overhead, and can suffer from expert imbalance. We propose AoE-MTL, a gate-free expert architecture where experts self-activate using task-specific L2-norms of their outputs.
Enkhbayar, Anand, Bea, Khean Thye, Wang, Chien-Yao, Huang, Chieh-Sheng, Chen, Yen-Lin   +4 more
openaire   +2 more sources

Information sharing methods for multi-task learning [PDF]

, 2022
This thesis investigates information sharing for Multi-Task Learning (MTL) in the multimedia and computer vision domains. More specifically, we investigate how, when and where information sharing should occur, in order to maximize the positive, and ...
Strezoski, G.
core  

Mitigating bias in multi-task learning [PDF]

In this thesis, we focus on multi-task learning in computer vision. The goal of multi-task learning is to train several related and different tasks simultaneously and perform well on each task with bi-directional knowledge transfer among tasks. We aim to
Shen, J.
core   +3 more sources

Privacy-Preserving Multi-Task Learning

, 2018
Multi-task learning (MTL), improving learning performance by transferring information between related tasks, has drawn more and more attention in the data mining field.
Fu, Yanjie, Wei Jiang, Liu, Kunpeng, Jiang, Wei, Uplavikar, Nitish, Kunpeng Liu, Nitish Uplavikar, Yanjie Fu   +7 more
core   +1 more source

Knowledge-enhanced multi-task learning traffic incident detection model based on social media data

智能科学与技术学报
Traffic incident detection is a core component of intelligent transportation systems (ITS), but existing methods are limited in processing unstructured social media text, associated geographic information, and collaborative multi-task learning.
ZHOU Zheng, WANG Mei, YANG Linyao, LI Lifang, WANG Xiao   +4 more
doaj  

Adaptive edge-aware graph convolutional with multi-task learning for simultaneous prediction of material properties

npj Computational Materials
The targeted design of functional materials often requires the concurrent optimization of multiple interdependent properties. For boron-doped graphene (BDG), both the band gap and work function critically influence performance in electronic and catalytic
Yunhua Lu, Mingyue Chen, Qingwei Zhang, Junan Zhang, Chao Zhang, Shiai Xu, Qiuyan Bi   +6 more
doaj   +1 more source

Multi-task Learning for Software Agents

, 2007
This paper describes experiments done to demonstrate the effectiveness of Multi-task Learning (MTL) for software agents. The experiments were carried out on an agent for processing electronic mail (email).
Stephen A. Hockema
core