/Symbolic_DNN-Tuner

Symbolic DNN-Tuner is a system to drive the training of a Deep Neural Network, analysing the performance of each training experiment and automatizing the choice of HPs to obtain a network with better performance.

Primary LanguagePythonMIT LicenseMIT

Symbolic DNN-Tuner

Symbolic DNN-Tuner is a system to drive the training of a Deep Neural Network, analysing the performance of each training experiment and automatizing the choice of HPs to obtain a network with better performance.

Publications

[1] Michele Fraccaroli, Evelina Lamma & Fabrizio Riguzzi (2021): Symbolic DNN-Tuner. Machine Learning, pp. 1–26, doi:10.1007/s10994-021-06097-1.
[2] Michele Fraccaroli, Evelina Lamma & Fabrizio Riguzzi (2022): Symbolic DNN-Tuner: A Python and ProbLog-based system for optimizing Deep Neural Networks hyperparameters. SoftwareX 17, p. 100957, doi:10.1016/j.softx.2021.100957.

Bibitex Citations

@article{fraccaroli2022symbolic,
  title={Symbolic DNN-tuner},
  author={Fraccaroli, Michele and Lamma, Evelina and Riguzzi, Fabrizio},
  journal={Machine Learning},
  volume={111},
  number={2},
  pages={625--650},
  year={2022},
  publisher={Springer}
}
@article{fraccaroli2022symbolic,
  title={Symbolic DNN-Tuner: A Python and ProbLog-based system for optimizing Deep Neural Networks hyperparameters},
  author={Fraccaroli, Michele and Lamma, Evelina and Riguzzi, Fabrizio},
  journal={SoftwareX},
  volume={17},
  pages={100957},
  year={2022},
  publisher={Elsevier}
}