Loading...
The Improved Training Algorithm of Deep Learning with Self-Adaptive Learning Rate
Author(s)
Date Issued
December 24, 2018
Type
Conference Paper
Abstract
This paper proposed the improvement of convergence performance for deep learning. For traditional algorithm, the learning rate is depended on experience and experiment. In this work, the learning rate can be adaptived based on Taylor's formula. This formula has the relationship between the root mean square errors changed, connection template, weights and biases changes are obtained. The proposed self-Adaptive learning rate is depended on neural network structure, root mean square error and error curve surface gradient. From the results, this proposed system has iteration times less than the traditional algorithm with constant learning rate.
Citation
Iscit 2018 18th International Symposium on Communication and Information Technology, 463-466, 2018