Restricted Boltzmann machine to determine the input weights for extreme learning machines

作者：

Highlights：

• The extreme learning machine’s weights initialization problem is tackled.

• The restricted Boltzmann machine is used to determine the ELM input weights.

• The proposed approach is applied to standard classification benchmarks.

• The results present promising performance compared with other well-known approaches.

摘要

•The extreme learning machine’s weights initialization problem is tackled.•The restricted Boltzmann machine is used to determine the ELM input weights.•The proposed approach is applied to standard classification benchmarks.•The results present promising performance compared with other well-known approaches.

论文关键词：Neural networks,Extreme learning machine,Restricted Boltzmann machine,Weights initialization

论文评审过程：Received 16 August 2017, Revised 7 November 2017, Accepted 28 November 2017, Available online 29 November 2017, Version of Record 22 December 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.054