A near effective and efficient model in recognition

作者：

Highlights：

• Propose Cycle Reinforce Hierarchical Model for recognition tasks.

• Design hierarchical structure composed of several hidden layers for features evolution.

• Adopt groups of fuzzy subsystems with fuzzy rules ensures the diversity of features.

• Introduce cycle mechanism for transferring refined coefficients.

• Measure innovative strategies by the perspective of contribution rate.

摘要

•Propose Cycle Reinforce Hierarchical Model for recognition tasks.•Design hierarchical structure composed of several hidden layers for features evolution.•Adopt groups of fuzzy subsystems with fuzzy rules ensures the diversity of features.•Introduce cycle mechanism for transferring refined coefficients.•Measure innovative strategies by the perspective of contribution rate.

论文关键词：Pattern recognition,Hierarchical structure,Fuzzy system,Cycle mechanism

论文评审过程：Received 5 February 2020, Revised 3 June 2021, Accepted 6 July 2021, Available online 27 July 2021, Version of Record 26 August 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108173