.png){kind=icon}
返回
Transfer Learning Algorithm With Knowledge Division Level
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3151646.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
One of the major challenges of transfer learning algorithms is the domain drifting problem where the knowledge of source scene is inappropriate for the task of target scene. To solve this problem, a transfer learning algorithm with knowledge division level (KDTL) is proposed to subdivide knowledge of source scene and leverage them with different drifting degrees. The main properties of KDTL are three folds. First, a comparative evaluation mechanism is developed to detect and subdivide the knowledge into three kinds--the ineffective knowledge, the usable knowledge, and the efficient knowledge. Then, the ineffective and usable knowledge can be found to avoid the negative transfer problem. Second, an integrated framework is designed to prune the ineffective knowledge in the elastic layer, reconstruct the usable knowledge in the refined layer, and learn the efficient knowledge in the leveraged layer. Then, the efficient knowledge can be acquired to improve the learning performance. Third, the theoretical analysis of the proposed KDTL is analyzed in different phases. Then, the convergence property, error bound, and computational complexity of KDTL are provided for the successful applications. Finally, the proposed KDTL is tested by several benchmark problems and some real problems. The experimental results demonstrate that this proposed KDTL can achieve significant improvement over some state-of-the-art algorithms.
Keyword:
Transfer learning
Task analysis
Learning systems
Knowledge engineering
Prediction algorithms
Measurement
Predictive models
Domain drifting problem
hierarchal transfer learning algorithm
integrated learning method
negative transfer
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
.png){kind=icon}
Improving the Properties of Self-compacted Concrete with Using Combined Silica Fume and Metakaolin
OAAI
OAAI分享收藏Deep Transfer Learning Based on Sparse Autoencoder for Remaining Useful Life Prediction of Tool in Manufacturing基于稀疏自编码器的深度迁移学习在制造业刀具剩余寿命预测中的应用
PREAI
分享收藏Deep Additive Least Squares Support Vector Machines for Classification With Model Transfer基于模型转移的深度加法最小二乘支持向量机分类OAAI
OAAI分享收藏
查看更多内容