Lib
Project description
This contains Feedforward and Recurrent neural networks
Features
- Feedforward and Recurrent neural nets
- Contains logistic, tanh, ReLU, softmax neurons
- Standard loss functions (squared error, cross entropy, sparsity constraints), and support for custom loss functions
- Different methods to initialize weights
- Customizable connectivity between layers
- Inputs can be generated dynamically by some other system (like a simulation)
Quick start
Install the package via:
pip install gaunn
Requirements
- python 2.7 or 3.5
- numpy 1.9.2
- matplotlib 1.3.1
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
| Filename, size | File type | Python version | Upload date | Hashes |
|---|---|---|---|---|
| Filename, size gaunn-1.0.0-py2-none-any.whl (37.4 kB) | File type Wheel | Python version py2 | Upload date | Hashes View |
| Filename, size gaunn-1.0.0.tar.gz (32.2 kB) | File type Source | Python version None | Upload date | Hashes View |