On the comparison of random and Hebbian weights for the training of single-hidden layer feedforward neural networks

作者：

Highlights：

• An extensive comparison of Hebbian and Random input weights in SLFN networks.

• A novel fusion scheme for merging Hebbian and Random feature spaces is proposed.

• The suggested linear combination of both feature spaces results in more robustness.

摘要

•An extensive comparison of Hebbian and Random input weights in SLFN networks.•A novel fusion scheme for merging Hebbian and Random feature spaces is proposed.•The suggested linear combination of both feature spaces results in more robustness.

论文关键词：Hebbian learning,Oja’s rule,Random feature space,Graph embedding,SLFN

论文评审过程：Received 3 January 2017, Revised 28 March 2017, Accepted 13 April 2017, Available online 25 April 2017, Version of Record 28 April 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.04.025