Welcome to RosenPy’s documentation!

What is RosenPy?

• 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 (com-plex-valued radial basis function neural network), FC-RBFNN (fully-complex radial basis function neural network), and PT-RBFNN (deep phase transmittance radial basis function neural network);

• It enables the incorporation of properties intrinsic to neural networks, such as L2 regularization, optimization, early stopping, mini-batch, and learning rate decay.

Dependencies

Python3.6+, Numpy, Cupy

Features and Benefits

RosenPy is easy to use, has a fast learning curve for the end-user, and is implemented in one of the most popular programming languages available today. Additionally, the framework incorporates several features that aid in optimizing complex-valued prediction problems. In addition, the API is consistent, straightforward, extensible, and has a simple structure. It supports five different complex-valued neural networks that the end-user can easily model and train by simple configuration of their hyperparameters.