Incremental learning model inspired in Rehearsal for deep convolutional networks
作者：
Highlights：
• An incremental learning model inspired in Rehearsal (recall of past memories based on a subset of data) is proposed.
• Experiments were performed over MNIST, Fashion-MNIST, CIFAR-10 and Caltech 101 in two different scenarios.
• Several metrics were used to compare learning quality results when each new megabatch of data is used.
• Friedman’s non-parametric statistical test and Holm post-hoc test were used for supporting the analysis of the results.
• Random-based selection of representative samples obtains the best results.
摘要
•An incremental learning model inspired in Rehearsal (recall of past memories based on a subset of data) is proposed.•Experiments were performed over MNIST, Fashion-MNIST, CIFAR-10 and Caltech 101 in two different scenarios.•Several metrics were used to compare learning quality results when each new megabatch of data is used.•Friedman’s non-parametric statistical test and Holm post-hoc test were used for supporting the analysis of the results.•Random-based selection of representative samples obtains the best results.
论文关键词：Artificial Neural Network,Deep Learning,Deep convolutional networks,Rehearsal,Incremental learning
论文评审过程：Received 27 April 2020, Revised 29 July 2020, Accepted 2 September 2020, Available online 16 September 2020, Version of Record 28 September 2020.
论文官网地址：https://doi.org/10.1016/j.knosys.2020.106460
