Gradient Boosted Neural Network-Multi-Output or GBNN-MO model is a novel training procedure for shallow and deep neural networks. The GBNN-MO is specifically developed for single and multi-output regression problems. The GBNN-MO is developed over the GBNN model.

The focus of this package is to provide related examples of the paper's experiments and results. You can reproduce our paper's results with the help of this package.

The described and developed method is based on the GBNN paper. The main algorithm and codes are stored here.

To run the examples of this package, you have to install the GBNN package from here.

pip install gbnn

To cite the paper, use the following BibTex format

@inproceedings{DBLP:conf/esann/EmamiM22,
  author       = {Seyedsaman Emami and
                  Gonzalo Mart{\'{\i}}nez{-}Mu{\~{n}}oz},
  title        = {Multioutput Regression Neural Network Training via Gradient Boosting},
  booktitle    = {30th European Symposium on Artificial Neural Networks, Computational
                  Intelligence and Machine Learning, {ESANN} 2022, Bruges, Belgium,
                  October 5-7, 2022},
  year         = {2022},
  url          = {https://doi.org/10.14428/esann/2022.ES2022-95},
  doi          = {10.14428/esann/2022.ES2022-95}
}

• Gonzalo Martínez-Muñoz
• Seyedsaman Emami

0.0.2

01 Jul 2022

01 Jan 2022