A zeroing neural dynamics based acceleration optimization approach for optimizers in deep neural networks.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

The first-order optimizers in deep neural networks (DNN) are of pivotal essence for a concrete loss function to reach the local minimum or global one on the loss surface within convergence time. However, each optimizer possesses its own superiority and virtue when encountering a specific application scene and environment. In addition, the existing modified optimizers mostly emphasize a given optimizer without any transfer property. In this paper, a zeroing neural dynamics (ZND) based optimization approach for the first-order optimizers is proposed, which can assist ZND via the activation function to expedite the process of solving gradient information, with lower loss and higher accuracy. To the best of our knowledge, it is the first work to integrate the ZND in control domain with the first-order optimizers in DNN. This generic work is an optimization method for the most commonly-used first-order optimizers to handle different application scenes, rather than developing a brand-new algorithm besides the existing optimizers or their modifications. Furthermore, mathematic derivations concerning the gradient information transformation of the ZND are systematically provided. Finally, comparison experiments are implemented, which demonstrates the effectiveness of the proposed approach with different loss functions and network frameworks on the Reuters, CIFAR, and MNIST data sets.

Authors

  • Shan Liao
    School of Cyber Science and Engineering, Sichuan University, Chengdu 610065, China.
  • Shubin Li
    School of Cyber Science and Engineering, Sichuan University, Chengdu 610065, China.
  • Jiayong Liu
    College of Cybersecurity, Sichuan University, Chengdu 610065, China.
  • Haoen Huang
    College of Electronic and Information Engineering, Guangdong Ocean University, Zhanjiang 524088, China.
  • Xiuchun Xiao
    College of Electronics and Information Engineering, Guangdong Ocean University, Zhanjiang 524025, China.