首页|Griffiths' Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks

Griffiths' Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks

扫码查看
原文链接
  • NSTL
  • Pleiades Publishing Inc
For online sequential training of deep neural networks, where the training data set is chaotic in nature, it becomes quite challenging for choosing a proper learning rate. This paper presents Griffiths' variable learning rate algorithm for improved performance of online sequential learning of feed-forward neural networks used for chaotic time-series prediction. Here, the learning rate is varied based on Griffiths' cross-correlation between input training data and squared error, which facilitates better tracking of time-series data.

Griffiths variable learning rate online sequential learning (GVLR-OSL)fixed learning rate online sequential learning (FLR-OSL)single hidden layer feedforward neural networks (SHLFN)stochastic gradient descent back-propagation (SGBP)

Bharath, Y. K.

展开 >

Visvesvaraya Technol Univ

2022

10.3103/S0146411622020031

Automatic Control and Computer Sciences

Automatic Control and Computer Sciences

EIESCI
ISSN：0146-4116
年,卷(期)：2022.56(2)
  • 2
  • 13