numpy-nn 0.2.6

Numpy NN is a Deep Neural Network Package which is built on base Numpy operations. This project is under development and any contributions are welcome.

numpy_nn

Numpy NN is a Deep Neural Network Package which is built on base Numpy operations. This project is under development and any contributions are welcome.

• Free software: MIT license

• Documentation: https://numpy-nn.readthedocs.io.

Features

• Layers: (Neurons)

• Losses: (Mean Absolute Error, Mean Squared Error, Binary Cross Entropy, Cross Entropy)

• Optimizer: (Stochastic Gradient Descent, RMSProp, Adam, Momentum)

• Activation: (ReLU, TanH, Sigmoid, LeakyReLU. ELU, Softmax)

• Layer Abstraction to implement custom activations and layers

• Persist model for later reuse.

TODO

• Implementation of different Losses

• Distributed Computation or GPU utilization

• Dataset processing utilities

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.

History

0.1.0 (2020-05-10)

• First release on PyPI.