A Novel Fractional Gradient-Based Learning Algorithm for Recurrent Neural Networks
Backpropagation
Identification
DOI:
10.1007/s00034-017-0572-z
Publication Date:
2017-05-22T08:25:24Z
AUTHORS (4)
ABSTRACT
In this research, we propose a novel algorithm for learning of the recurrent neural networks called as the fractional back-propagation through time (FBPTT). Considering the potential of the fractional calculus, we propose to use the fractional calculus-based gradient descent method to derive the FBPTT algorithm. The proposed FBPTT method is shown to outperform the conventional back-propagation through time algorithm on three major problems of estimation namely nonlinear system identification, pattern classification and Mackey–Glass chaotic time series prediction.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (70)
CITATIONS (40)
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....