An online learning algorithm for adaptable topologies of neural networks

作者：

Highlights：

• We proposed an online learning algorithm for feedforward neural networks.

• The learning method allows the dynamic incorporation of hidden neurons.

• It can be used in non-stationary problems allowing adaptation to changes.

摘要

•We proposed an online learning algorithm for feedforward neural networks.•The learning method allows the dynamic incorporation of hidden neurons.•It can be used in non-stationary problems allowing adaptation to changes.

论文关键词：Incremental learning,Sequential learning,Forgetting ability,Adaptive topology

论文评审过程：Available online 9 July 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.06.066