- A complex-valued neural network library, written in Python;
- Incorporates CVNNs such as CV-FFNN (complex-valued feedforward neural network), SC-FFNN (split-complex feedforward neural network), CV-RBFNN (complex-valued radial basis function neural network), FC-RBFNN (fully-complex radial basis function neural network), and PT-RBFNN (phase transmittance radial basis function neural network);
- It enables the incorporation of properties intrinsic to neural networks, such as L2 regularization, optmization, early stopping, mini-batch, and learning rate decay.
- For more information about the documentation, visit: https://ariadneac.github.io/rosenpy-v2.1/
- Python3.6+, Numpy, Cupy
- Ariadne Arrais Cruz – [email protected]
- Kayol Soares Mayer – [email protected]
- Dalton Soares Arantes – [email protected]
RosenPy is an open source framework distributed under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
RosenPy is distributed in the hope that it will be useful to every user, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public Licens for more details.
Please contact the authors or Inova/Unicamp ([email protected]) for commercial use permissions, premium support or customized solutions based on RosenPy.
We kindly ask that reference to RosenPy should be done as:
@ARTICLE{Ariadne2022, author = {Ariadne Arrais Cruz, Kayol Soares Mayer, Dalton Soares Arantes}, title = {{RosenPy: an Open Source Python Framework for Complex-Valued Neural Networks}}, journal = {Software X}, year = {2024}, volume = {??}, number = {??}, pages = {?-??}, doi={??} }