Results 251 to 260 of about 83,974 (281)

Meta weight learning via model-agnostic meta-learning

Neurocomputing, 2021
Abstract While meta learning approaches have achieved remarkable success, obtaining a stable and unbiased meta-learner remains a significant challenge, since the initial model of a meta-learner could be too biased towards existing tasks to adapt to new tasks.
Zhixiong Xu, Xiliang Chen, Wei Tang, Jun Lai, Lei Cao   +4 more
openaire   +1 more source

Modified Model-Agnostic Meta-Learning

2020 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT), 2020
Meta-learning, an idea of "learning to learn," is a machine learning field that applies a learning algorithm to train a model for performing various tasks. This paper extends the current version of meta-learning by applying a modified model-agnostic algorithm so that the model becomes capable of performing the tasks just upon being trained on a few ...
openaire   +1 more source

The Research about Recurrent Model-Agnostic Meta Learning

Optical Memory and Neural Networks, 2020
Although Deep Neural Networks (DNNs) have performed great success in machine learning domain, they usually show poorly on few-shot learning tasks, where a classifier has to quickly generalize after getting very few samples from each class. A Model-Agnostic Meta Learning (MAML) model, which is able to solve new learning tasks, only using a small number ...
null Shaodong Chen, null Ziyu Niu
openaire   +1 more source

Specific Emitter Identification via Sparse Bayesian Learning Versus Model-Agnostic Meta-Learning

IEEE Transactions on Information Forensics and Security, 2023
Specific emitter identification (SEI) is a technique to identify the unknown emitters by using the hardware impairment of the transmitter. In this paper, we consider the effect of the wireless channel on the SEI, which deteriorates the identification ...
Boxiang He, Fanggang Wang
semanticscholar   +1 more source

Few-Shot Network Intrusion Detection Based on Model-Agnostic Meta-Learning with L2F Method

IEEE Wireless Communications and Networking Conference, 2023
Network Intrusion Detection (NID) plays an important role in identifying network threats and ensuring the security of computer and communication systems.
Zhixin Shi, Mengyan Xing, Jing Zhang, Hao Wu   +3 more
semanticscholar   +1 more source

Small sample classification of hyperspectral image using model-agnostic meta-learning algorithm and convolutional neural network

International Journal of Remote Sensing, 2021
The difficulties of obtaining sufficient high-quality labelled samples have always been one of the important factors hindering the practical application of hyperspectral images (HSI) classification.
Kuiliang Gao, Bing Liu, Xuchu Yu, Pengqiang Zhang, Xiong Tan, Yifan Sun   +5 more
semanticscholar   +1 more source

Short-term Load Forecasting of Distribution Transformer Supply Zones Based on Federated Model-Agnostic Meta Learning

IEEE Transactions on Power Systems
With the increasing data privacy concerns raised by not only organizations but also individuals in distribution systems, traditional centralized data-driven forecasting approaches for short-term load forecasting (STLF) in distribution transformer supply ...
Changsen Feng, Liang Shao, Jiaying Wang, Youbing Zhang, Fushuan Wen   +4 more
semanticscholar   +1 more source

Transferrable Model-Agnostic Meta-learning for Short-Term Household Load Forecasting With Limited Training Data

IEEE Transactions on Power Systems, 2022
This letter proposes a transferrable model-agnostic meta-learning (T-MAML) approach for short-term load forecasting for single households. The proposed approach enables multiple households to collaboratively train a generic artificial neural network (ANN)
Yu He, Fengji Luo, G. Ranzi
semanticscholar   +1 more source

MAML-KalmanNet: A Neural Network-Assisted Kalman Filter Based on Model-Agnostic Meta-Learning

IEEE Transactions on Signal Processing
Neural network-assisted (NNA) Kalman filters provide an effective solution to addressing the filtering issues involving partially unknown system information by incorporating neural networks to compute the intermediate values influenced by unknown data ...
Shanli Chen, Yunfei Zheng, Dongyuan Lin, Peng Cai, Yingying Xiao, Shiyuan Wang   +5 more
semanticscholar   +1 more source

Question-Answer Methodology for Vulnerable Source Code Review via Prototype-Based Model-Agnostic Meta-Learning

Future Internet
In cybersecurity, identifying and addressing vulnerabilities in source code is essential for maintaining secure IT environments. Traditional static and dynamic analysis techniques, although widely used, often exhibit high false-positive rates, elevated ...
Pablo Corona-Fraga, Aldo Hernandez-Suarez, G. Sánchez-Pérez, L. K. Toscano-Medina, H. Perez-Meana, J. Portillo-Portillo, J. Olivares-Mercado, L. J. García Villalba   +7 more
semanticscholar   +1 more source