【会议论文】深度卷积神经网络超参数自动优化：基于坐标上升改进的网格搜索

SOONG, CHINGTSING

May 31, 2024

124 views

No comments

2149 words

科学研究

> 于2024年05月31日在MIDA2024会议中报告并即将发表于MIDA论文集（EI检索）中。

##Title

Automatic Optimization of Hyperparameters for Deep Convolutional Neural Networks: Grid Search Enhanced with Coordinate Ascent

## Author

**Qingqing Song***
Belarusian State University, Faculty of Applied Mathematics and Computer Science, Minsk, Belarus, fpm.sunC@bsu.by

**Shaoliang Xia**

Belarusian State University, Faculty of Applied Mathematics and Computer Science, Minsk, Belarus, fpm.sya@bsu.by

**Zhen Wu**
Nanjing University of Aeronautics and Astronautics, Nanjing, China, 13wuzhen@sina.com

## Abstract

Using the same depth convolutional neural network model will result in significantly different results due to different combinations of hyperparameters. By adjusting the configuration of hyperparameters, we can enhance the performance of the model. However, hyperparameter optimization typically requires a significant amount of computational resources and time. Therefore, improving the efficiency of hyperparameter optimization is crucial. In this study, we utilized the coordinate ascent method, which only offered initial candidate values for each hyperparameter. By changing only the hyperparameter that had the greatest effect on the model in each iteration, we gradually expanded the search grid until we achieved convergence in accuracy. This method enables us to effectively and automatically find hyperparameter combinations that can improve model accuracy. The experimental results show that using the MWD dataset, the model optimized through hyperparameters achieved an accuracy of 95.71% on the validation set, and this hyperparameter combination can be considered an approximate global optimal solution. In addition, the performance of the hyperparameter combination in its neighborhood is stable, which further proves the robustness of our hyperparameter optimization strategy.

## CCS CONCEPTS

Computing methodologies∼Machine learning∼Learning settings

## Additional Keywords and Phrases

Deep convolutional neural network, Hyperparameter optimization, Coordinate ascent, Grid search, Machine learning, Optimization strategy

【会议论文】深度卷积神经网络超参数自动优化：基于坐标上升改进的网格搜索

SOONG, CHINGTSING • 2024 年 05 月 31 日

【会议论文】深度卷积神经网络超参数自动优化：基于坐标上升改进的网格搜索

Leave a Comment Cancel reply
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款

【吉他谱】Aloha Heja He 指弹

【吉他谱】打上花火指弹版

【吉他谱】城南花已开指弹版

【吉他谱】Take Me Hand 指弹版

【吉他谱】溯指弹版

杂文#1 - 旅游延期..延期..延期..

【飞飞】Bubble注册器支持GM账号注册

【吉他练习】第一阶段500小时记录日志

【吉他谱】打上花火指弹版

【吉他谱】一曲相思指弹版

【会议论文】深度卷积神经网络超参数自动优化：基于坐标上升改进的网格搜索

Leave a Comment Cancel reply 使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款

【会议论文】深度卷积神经网络超参数自动优化：基于坐标上升改进的网格搜索

Leave a Comment Cancel reply
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款