PID controller‐based adaptive gradient optimizer for deep neural networks-Reference-Cited by-同舟云学术

PID controller‐based adaptive gradient optimizer for deep neural networks

Published:2022-11-26 Issue: Volume: Page:
ISSN:1751-8644
Container-title:IET Control Theory & Applications
language:en
Short-container-title:IET Control Theory & Appl

Author:

Dai Mingjun¹^ORCID,Zhang Zelong¹,Lai Xiong¹,Lin Xiaohui¹,Wang Hui²

Affiliation:

1. Guangdong Provincial Engineering Center for Ubiquitous Computing and Intelligent Networking Department of Communication, College of Electronic and Information Engineering Shenzhen University Shenzhen 518060 China

2. Department of CommunicationShenzhen Institute of Information Technology Shenzhen China

Funder

National Natural Science Foundation of China

Publisher

Institution of Engineering and Technology (IET)

Subject

Electrical and Electronic Engineering,Control and Optimization,Computer Science Applications,Human-Computer Interaction,Control and Systems Engineering

Link

https://onlinelibrary.wiley.com/doi/pdf/10.1049/cth2.12404

Reference32 articles.

1. Learning to Optimize: Reference Vector Reinforcement Learning Adaption to Constrained Many-Objective Optimization of Industrial Copper Burdening System

2. Deep Reinforcement Learning

3. TCDA: truthful combinatorial double auctions for mobile edge computing in industrial Internet of Things;Ma L.;IEEE Trans. Mob. Comput,2021

4. Deep learning

5. Dauphin Y.N. Pascanu R. et al.:Identifying and attacking the saddle point problem in high‐dimensional non‐convex optimization. In:Proceedings of the 27th International Conference on Neural Information Processing Systems pp.2933–2941.ACM Press New York(2014)

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Enhancing deep neural network training efficiency and performance through linear prediction;Scientific Reports;2024-07-02

2. Intelligent Regulation of Temperature and Humidity in Vegetable Greenhouses Based on Single Neuron PID Algorithm;Electronics;2024-05-27