Random vector functional link neural network based ensemble deep learning

作者：

Highlights：

• Inspired by the principles of Random Vector Functional Link (RVFL) network, we propose a deep RVFL network (dRVFL) with rich feature extraction capabilities through several hidden layers.

• We also propose an ensemble deep network (edRVFL) based on a single dRVFL network.

• We demonstrate the generic nature of the proposed methods by integrating them with a recent RVFL variant called sparse-pretrained RVFL (SP-RVFL).

• Experiments on 46 tabular UCI classification datasets demonstrate that the proposed ensemble deep RVFL networks outperform state-of-the-art deep feed-forward neural networks.

• Experiments on 12 sparse classification datasets demonstrate that the proposed ensemble deep SP-RVFL networks outperform the best.

摘要

•Inspired by the principles of Random Vector Functional Link (RVFL) network, we propose a deep RVFL network (dRVFL) with rich feature extraction capabilities through several hidden layers.•We also propose an ensemble deep network (edRVFL) based on a single dRVFL network.•We demonstrate the generic nature of the proposed methods by integrating them with a recent RVFL variant called sparse-pretrained RVFL (SP-RVFL).•Experiments on 46 tabular UCI classification datasets demonstrate that the proposed ensemble deep RVFL networks outperform state-of-the-art deep feed-forward neural networks.•Experiments on 12 sparse classification datasets demonstrate that the proposed ensemble deep SP-RVFL networks outperform the best.

论文关键词：Random Vector Functional Link (RVFL),Deep RVFL,Multi-layer RVFL,Ensemble deep learning,Randomized neural network,Extreme learning machine (ELM)

论文评审过程：Received 16 May 2020, Revised 29 November 2020, Accepted 31 March 2021, Available online 20 April 2021, Version of Record 4 May 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107978