Quality of randomness and node dropout regularization for fitting neural networks

作者：

Highlights：

• Quality of randomness associated with neural network regularization investigated.

• Pseudorandom and true random number generators were compared.

• Statistical randomness of node dropout can affect overfitting of models.

• Random number experimentation proposed for fitting neural networks.

摘要

•Quality of randomness associated with neural network regularization investigated.•Pseudorandom and true random number generators were compared.•Statistical randomness of node dropout can affect overfitting of models.•Random number experimentation proposed for fitting neural networks.

论文关键词：Quality of randomness,Node dropout,Neural network,True random number,Quantum random number generation

论文评审过程：Received 10 February 2022, Revised 2 May 2022, Accepted 19 June 2022, Available online 26 June 2022, Version of Record 30 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117938