Forgetting of unused classes in missing data environment using automatically generated data: Application to on-line handwritten gesture command recognition
作者：
Highlights：
• A new framework for the incorporation of generation of synthetic data into the on-line learning process.
• Application of our novel technique to treat the problem of forgetting of unused classes in an on-line learning environment.
• Empirical estimation of the amount of synthetic data to be generated.
• Empirical estimation of the duration of the generation of synthetic data.
• Evaluation of the results on several scenarios.
摘要
•A new framework for the incorporation of generation of synthetic data into the on-line learning process.•Application of our novel technique to treat the problem of forgetting of unused classes in an on-line learning environment.•Empirical estimation of the amount of synthetic data to be generated.•Empirical estimation of the duration of the generation of synthetic data.•Evaluation of the results on several scenarios.
论文关键词：On-line learning,Handwritten gesture command recognition,TS-Fuzzy models,ARTIST,Synthetic data,Forgetting of unused classes,Elastic memory learning,Kinematic theory
论文评审过程：Received 9 October 2016, Revised 30 July 2017, Accepted 3 August 2017, Available online 8 August 2017, Version of Record 17 August 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.08.007
