Comparing of deep neural networks and extreme learning machines based on growing and pruning approach

作者：

Highlights：

• Deep Neural Networks and Extreme Learning Machines based models are designed.

• The effectiveness of growing and pruning approach is examined on these models.

• Deep Neural Networks models are designed by utilizing ‘Keras’ library.

• Extreme Learning Machines are designed by utilizing ‘hpelm’ library.

• Deep neural Networks performed better or comparable to the Extreme Learning Machines.

摘要

•Deep Neural Networks and Extreme Learning Machines based models are designed.•The effectiveness of growing and pruning approach is examined on these models.•Deep Neural Networks models are designed by utilizing ‘Keras’ library.•Extreme Learning Machines are designed by utilizing ‘hpelm’ library.•Deep neural Networks performed better or comparable to the Extreme Learning Machines.

论文关键词：Deep Neural Networks,Extreme Learning Machines,Growing and pruning,Parkinson,Self-care activities

论文评审过程：Received 8 June 2019, Revised 30 July 2019, Accepted 15 August 2019, Available online 16 August 2019, Version of Record 21 August 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112875