.png){kind=icon}
返回
Decoder Choice Network for Metalearning
.png){kind=icon}
OA
AI
DOI：10.1109/TCYB.2021.3123403.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Metalearning has been widely applied for implementing few-shot learning and fast model adaptation. Particularly, existing metalearning methods have been exploited to learn the control mechanism for gradient descent processes, in an effort to facilitate gradient-based learning in gaining high speed and generalization ability. This article presents a novel method that controls the gradient descent process of the model parameters in a neural network, by limiting the model parameters within a low-dimensional latent space. The main challenge for implementing this idea is that a decoder with many parameters may be required. To tackle this problem, the article provides an alternative design of the decoder with a structure that shares certain weights, thereby reducing the number of required parameters. In addition, this work combines ensemble learning with the proposed approach to improve the overall learning performance. Systematic experimental studies demonstrate that the proposed approach offers results superior to the state of the art in performing the Omniglot classification and miniImageNet classification tasks.
Keyword:
Task analysis
Decoding
Training
Testing
Measurement
Optimization
Mathematical models
Decoder
ensemble learning
latent variable
metalearning
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
分享收藏Service-Related Exposures and Physical Health Trajectories Among Aging Veteran Men老年退伍军人中与服务相关的暴露和身体健康轨迹OAAI
OAAI分享收藏Skyrmion-electronics: writing, deleting, reading and processing magnetic skyrmions toward spintronic applicationsSkyrmion-电子学: 用于自旋电子应用的写入，删除，读取和处理磁性Skyrmion
OAAI
OAAI分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏Human-level concept learning through probabilistic program induction通过概率程序归纳进行人类水平的概念学习.png)
SCIENCEOAAI
SCIENCEIF45.8
OAAI分享收藏
查看更多内容