.png){kind=icon}
返回
Deterministic learning-based neural identification and knowledge fusion
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2023.10.004.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent deterministic learning methods have achieved locally-accurate identification of unknown system dynamics. However, the locally-accurate identification means that the neural networks can only capture local dynamics knowledge along the system trajectory. In order to capture a broader knowledge region, article investigates the knowledge fusion problem of deterministic learning, that is, the integration of different knowledge regions along different individual trajectories. Specifically, two kinds of knowledge fusion schemes are systematically introduced: an online fusion scheme and an offline fusion scheme. The online scheme be viewed as an extension of distributed cooperative learning control to cooperative neural identification for sampled-data systems. By designing an auxiliary information transmission strategy to enable the neural network to receive information learned from other tasks while learning its own task, it is proven that weights of all localized RBF networks exponentially converge to their common true/ideal values. The offline scheme can be regarded as a knowledge distillation strategy, in which the fused network is obtained by offline training through the knowledge learned from all individual system trajectories via deterministic learning. novel weight fusion algorithm with low computational complexity is proposed based on the least squares solution under subspace constraints. Simulation studies show that the proposed fusion schemes can successfully integrate the knowledge regions of different individual trajectories while maintaining the learning performance, thereby greatly expanding the knowledge region learned from deterministic learning.
Keyword:
Deterministic learning
Adaptive learning
Persistently exciting
Sampled-data system
Knowledge fusion
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Synthesis of GABA-Analogous Spirocyclic Amino Acids, 4. N-Benzyl-2-azaspiro[4.4]nonane-6-carboxylates.png)
HETEROCYCLESOAAI
HETEROCYCLESIF0
OAAI分享收藏Fusion of spatial-temporal and kinematic features for gait recognition with deterministic learning融合时空特征和运动学特征的步态识别与确定性学习PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Spatial and Temporal Distribution of Phytoplankton in Perak Estuary, Malaysia, During Monsoon Season
OAAI
OAAI分享收藏On-line identification of nonlinear systems using Volterra polynomial basis function neural networksNEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏
查看更多内容