Results 21 to 30 of about 60,811 (193)

Robust Compare Network for Few-Shot Learning

IEEE Access, 2020
Making machines learn like humans is the ultimate goal of artificial intelligence. Few-shot learning attempts to simulate the learning mechanism of humans, which is a task that can learn novel concepts from very few labeled samples.
Yixin Yang, Yang Li, Rui Zhang, Jiabao Wang, Zhuang Miao   +4 more
doaj   +1 more source

Structure-Aware Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

Mathematics, 2023
With the growing scale of pre-trained language models (PLMs), full parameter fine-tuning becomes prohibitively expensive and practically infeasible.
Yahao Hu, Yifei Xie, Tianfeng Wang, Man Chen, Zhisong Pan   +4 more
doaj   +1 more source

Ontology Alignment Repair Through 0-1 Programming

IEEE Access, 2019
In order to solve the problem of lack of effective methods for ontology inconsistency, a user preferences-oriented ontology alignment repair model is proposed.
Wenning Hao, Junyue Chen, Gang Chen, Ruizhi Kang, Zixuan Zhang, Ao Zou   +5 more
doaj   +1 more source

Adaptive Constrained Differential Evolution Algorithm by Using Generalized Opposition-Based Learning

Xibei Gongye Daxue Xuebao, 2019
Differential evolution is a global optimization algorithm based on greedy competition mechanism, which has the advantages of simple structure, less control parameters, higher reliability and convergence. Combining with the constraint-handling techniques,

doaj   +1 more source

Adaptive Service Function Chain Scheduling in Mobile Edge Computing via Deep Reinforcement Learning

IEEE Access, 2020
MEC (Mobile Edge Computing) provides both IT service environment and cloud computation on the edge of the network. This technology not only minimizes the end-to-end latency but also increases the efficiency of computing.
Tianfeng Wang, Jiachen Zu, Guyu Hu, Dongyang Peng   +3 more
doaj   +1 more source

Contrastive Self-Supervised Hashing With Dual Pseudo Agreement

IEEE Access, 2020
Recently, unsupervised deep hashing has attracted increasing attention, mainly because of its potential ability to learn binary codes without identity annotations.
Yang Li, Yapeng Wang, Zhuang Miao, Jiabao Wang, Rui Zhang   +4 more
doaj   +1 more source

AI in Future C2 – Who’s in Command When AI Takes Control? [PDF]

, 2023
30.01.24: Source at https://internationalc2institute.org/.Artificial Intelligence (AI) will become an increasingly dominant element of future Command and Control (C2) systems and organizations.
Lund-Kordahl, Inger, Bjurström, Erik, Bakken, Bjørn Tallak   +2 more
core  

A Novel Multi-Agent Parallel-Critic Network Architecture for Cooperative-Competitive Reinforcement Learning

IEEE Access, 2020
Multi-agent deep reinforcement learning (MDRL) is an emerging research hotspot and application direction in the field of machine learning and artificial intelligence.
Yu Sun, Jun Lai, Lei Cao, Xiliang Chen, Zhixiong Xu, Yue Xu   +5 more
doaj   +1 more source

A Satellite Handover Strategy Based on the Potential Game in LEO Satellite Networks

IEEE Access, 2019
In a low earth orbit (LEO) satellite network, handover management across satellite spot beams needs to be addressed to decrease handover times while using network resources efficiently since the speed of LEO satellites is much higher than that of mobile ...
Yang Wu, Guyu Hu, Fenglin Jin, Jiachen Zu   +3 more
doaj   +1 more source

Multi-Level Metric Learning Network for Fine-Grained Classification

IEEE Access, 2019
The application of fine-grained image classification can be problematic due to subtle differences between classes. The existing global feature-based methods have worse accuracies than regional feature-based methods, because regional feature-based methods
Jiabao Wang, Yang Li, Zhuang Miao, Xun Zhao, Zhang Rui   +4 more
doaj   +1 more source