Optimal Architecture Deep Neural Network for Regression

These codes perform optimal architecture deep neural network model generation for regression problems and illustrate e-nose application.
55.0 次下载
更新时间 2024/3/27

查看许可证

Deep Neural Network (DNN) models require a suitable neural architecture (topology) for data driven modeling. Avoiding overfitting or underfitting problems and achieving a satisfactory generalization are main concerns in modeling tasks. To deal with these concerns, optimization of neural architecture according to the dataset is an effective solution.
These codes perform optimization of deep neural network model architecture for regression problems. An example is shown for e-nose application.

引用格式

Simsek, Ozlem Imik, and Baris Baykant Alagoz. “Optimal Architecture Artificial Neural Network Model Design with Exploitative Alpha Gray Wolf Optimization for Soft Calibration of CO Concentration Measurements in Electronic Nose Applications.” Transactions of the Institute of Measurement and Control, vol. 45, no. 4, SAGE Publications, Sept. 2022, pp. 686–99, doi:10.1177/01423312221119648.

查看更多格式

Alagoz, Baris Baykant, et al. “An Evolutionary Field Theorem: Evolutionary Field Optimization in Training of Power-Weighted Multiplicative Neurons for Nitrogen Oxides-Sensitive Electronic Nose Applications.” Sensors, vol. 22, no. 10, MDPI AG, May 2022, p. 3836, doi:10.3390/s22103836.

查看更多格式

İMİK ŞİMŞEK, Özlem, and Barış Baykant ALAGÖZ. “Model Based Demand Order Estimation by Using Optimal Architecture Artificial Neural Network with Metaheuristic Optimizations.” Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol. 12, no. 3, Igdir University, Sept. 2022, pp. 1277–91, doi:10.21597/jist.1099154.

查看更多格式
MATLAB 版本兼容性
创建方式 R2014b
兼容任何版本
平台兼容性
Windows macOS Linux
标签 添加标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
版本 已发布 发行说明
1.0.3

Some texts were improved in scripts.

1.0.2

Document was improved.

1.0.1

Readme file is improved.

1.0.0