Growing Echo State Network With an Inverse-Free Weight Update Strategy

Chen, Xiufang; Luo, Xin; Jin, Long; Li, Shuai; Liu, Mei

doi:10.1109/tcyb.2022.3155901

Cited by 16 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [12] designed reservoirs with predefined sparsity and singular values. Chen et al [13] constructed an incremental inverse-free ESN to obtain weights according to the information of the previous optimal reservoir state and the freshly added neurons in the reservoir. In order to update the input weights of simple cycle reservoir network (SCRN), Wang et al [14] injected the pre-trained output weight matrix into the input weight matrix, thus enabling the modification of the network weights.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised Echo State Network with Partial Correlation Pruning for Time-Series Variables Prediction in Industrial Processes

Huang¹,

Wang²,

Yang³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

For an ordinary echo state network (ESN), redundant information in the huge reservoir will lead to degradation of the prediction performance of the network, especially when the labels of the samples are limited. To solve this problem, a semi-supervised ESN with partial correlation pruning (PCP-S2ESN) is proposed in this paper to scientifically capture the essential association between two reservoir variables while controlling for the influence of other factors. In this way, redundant neurons and their connection weights in the reservoir are eliminated, so that the prediction accuracy is significantly enhanced by optimizing the network structure. Moreover, anunsupervised pre-training procedure is introduced to modify the input weight matrix and reservoir connection weight matrix of the ESN, which successfully achieves precise prediction of time-series variables with limited labels. The superiority of the PCP-S2ESN model is demonstrated through two benchmark prediction tasks and the fed-batch penicillin cultivation (FBPC) process.

show abstract

Section: Introductionmentioning

confidence: 99%