Results 31 to 40 of about 83,974 (281)

Off-Policy Meta-Reinforcement Learning With Belief-Based Task Inference

IEEE Access, 2022
Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for solving a new task.
Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka   +2 more
doaj   +1 more source

MW-MADDPG: a meta-learning based decision-making method for collaborative UAV swarm

Frontiers in Neurorobotics, 2023
Unmanned Aerial Vehicles (UAVs) have gained popularity due to their low lifecycle cost and minimal human risk, resulting in their widespread use in recent years.
Minrui Zhao, Gang Wang, Qiang Fu, Xiangke Guo, Yu Chen, Yu Chen, Tengda Li, XiangYu Liu   +7 more
doaj   +1 more source

Zero-Shot Cross-Lingual Transfer with Meta Learning

, 2020
Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance.
Augenstein, Isabelle, Bekoulis, Giannis, Bjerva, Johannes, Nooralahzadeh, Farhad   +3 more
core   +1 more source

Model-agnostic meta-learning-based region-adaptive parameter adjustment scheme for influenza forecasting

Journal of King Saud University: Computer and Information Sciences, 2023
Deep learning models perform well when there is enough data available for training, but otherwise the performance deteriorates rapidly owing to the so-called data shortage problem.
Jaeuk Moon, Yoona Noh, Sungwoo Park, Eenjun Hwang   +3 more
doaj   +1 more source

Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models [PDF]

, 2017
Volatility prediction--an essential concept in financial markets--has recently been addressed using sentiment analysis methods. We investigate the sentiment of annual disclosures of companies in stock markets to forecast volatility.
Anderson, Linda, Baklanov, Artem, Duer, Alexander, Hanbury, Allan, Lupu, Mihai, Rekabsaz, Navid   +5 more
core   +3 more sources

Research on Solid Motor Performance Prediction Method Based on Deep Meta-Learning [PDF]

Hangkong bingqi
Addressing the numerous limitations in solid motor performance experiments for aircraft power systems, such as high costs, specialized equipment requirements, specific experimental environments, and high risks, this paper proposes an artificial ...
Cui Yan, Lou Bixuan, Yu Pengcheng, Yang Huixin
doaj   +1 more source

Bayesian Model-Agnostic Meta-Learning

, 2018
First two authors contributed equally. 15 pages with appendix including experimental details.
Kim, Taesup, Yoon, Jaesik, Dia, Ousmane, Kim, Sungwoong, Bengio, Yoshua, Ahn, Sungjin   +5 more
openaire   +2 more sources

Meta-Learning via Weighted Gradient Update

IEEE Access, 2019
Despite deep reinforcement learning has attained performance beyond human beings in many domains, including games, dialogue systems and robotics, sample inefficient is still a limitation in the application of deep reinforcement learning.
Zhixiong Xu, Lei Cao, Xiliang Chen
doaj   +1 more source

Looking back to lower-level information in few-shot learning

, 2020
Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify new examples ...
Raschka, Sebastian, Yu, Zhongjie
core   +1 more source

Probabilistic Model-Agnostic Meta-Learning

, 2018
NeurIPS 2018. First two authors contributed equally. Supplementary results available at https://sites.google.com/view/probabilistic-maml/
Finn, Chelsea, Xu, Kelvin, Levine, Sergey   +2 more
openaire   +2 more sources