NAHL: a Neural network with an Augmented Hidden Layer

版本 2.4.0 (39.4 KB) 作者: BERGHOUT Tarek
An interesting new architecture for artificial neural networks
5.0
(1)
242.0 次下载
更新时间 2023/1/17

查看许可证

****The current version of NAHL is able to adapt with both classification and regession****
Please read these papers carefuly :
1) https://www.researchgate.net/publication/355985669_Auto-NAHL_A_Neural_Network_Approach_for_Condition-based_Maintenance_of_Complex_Industrial_Systems
2) https://www.researchgate.net/publication/361382499_EL-NAHL_Exploring_Labels_Autoencoding_in_Augmented_Hidden_Layers_of_Feedforward_Neural_Networks_for_Cybersecurity_in_Smart_Grids
Please cite our NAHL papers as:
[1] T. Berghout, M. Benbouzid, S. M. Muyeen, T. Bentrcia, and L.-H. Mouss, “Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems,” IEEE Access, vol. 9, pp. 152829–152840, 2021, doi: 10.1109/ACCESS.2021.3127084.
[2] T. Berghout and M. Benbouzid, “EL-NAHL: Exploring Labels Autoencoding in Augmented Hidden Layers of Feedforward Neural Networks for Cybersecurity in Smart Grids,” Reliab. Eng. Syst. Saf., p. 108680, Jun. 2022, doi: 10.1016/j.ress.2022.108680.
[3] T. Berghout, M. Benbouzid, Y. Amirat and G. Yao, "Lithium-ion Battery State of Health Prediction with a Robust Collaborative Augmented Hidden Layer Feedforward Neural Network Approach," in IEEE Transactions on Transportation Electrification, doi: 10.1109/TTE.2023.3237726.
MATLAB 版本兼容性
创建方式 R2018b
兼容任何版本
平台兼容性
Windows macOS Linux

Community Treasure Hunt

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

Start Hunting!

Auto_NAHL_codes

版本 已发布 发行说明
2.4.0

adding more references

2.3.0

New references have been added.
2.2.0

New published papers references has been added.
2.1.0

-New activation function ReLU
-Tolerance problem fixed
-Fitness function is replaced with RMSE loss function
-Adapting with both regression and classification

2.0.0

New activation function ReLU
Tolerance problem fixed
Fitness function is replaced with RMSE loss function
Adapting with both regression and classification

1.1.0

Citation is updated
1.0.0