A review on neural networks with random weights

Department

Computer Science

Document Type

Article

Publication Title

Neurocomputing

ISSN

0925-2312

Volume

275

Issue

31

DOI

10.1016/j.neucom.2017.08.040

First Page

278

Last Page

287

Publication Date

1-31-2018

Abstract

In big data fields, with increasing computing capability, artificial neural networks have shown great strength in solving data classification and regression problems. The traditional training of neural networks depends generally on the error back propagation method to iteratively tune all the parameters. When the number of hidden layers increases, this kind of training has many problems such as slow convergence, time consuming, and local minima. To avoid these problems, neural networks with random weights (NNRW) are proposed in which the weights between the hidden layer and input layer are randomly selected and the weights between the output layer and hidden layer are obtained analytically. Researchers have shown that NNRW has much lower training complexity in comparison with the traditional training of feed-forward neural networks. This paper objectively reviews the advantages and disadvantages of NNRW model, tries to reveal the essence of NNRW, gives our comments and remarks on NNRW, and provides some useful guidelines for users to choose a mechanism to train a feed-forward neural network.

Link to Full Text

Share

COinS