https://github.com/michabirklbauer/neuralnet
Neural Network Implementation in NumPy
https://github.com/michabirklbauer/neuralnet
backpropagation classification educational feedforward-neural-network from-scratch neural-network numpy
Last synced: 12 months ago
JSON representation
Neural Network Implementation in NumPy
- Host: GitHub
- URL: https://github.com/michabirklbauer/neuralnet
- Owner: michabirklbauer
- License: mit
- Created: 2022-12-27T20:57:23.000Z (about 3 years ago)
- Default Branch: master
- Last Pushed: 2022-12-30T21:59:38.000Z (about 3 years ago)
- Last Synced: 2025-01-04T07:52:41.766Z (about 1 year ago)
- Topics: backpropagation, classification, educational, feedforward-neural-network, from-scratch, neural-network, numpy
- Language: Jupyter Notebook
- Homepage: https://michabirklbauer.github.io/neuralnet
- Size: 8.83 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Neural Network Implementation in NumPy
A "from scratch" implementation of classic feed-forward neural networks for
binary/multi-class classification using ReLU activations, cross entropy loss and
sigmoid/softmax output.
Read through the documentation in `neuralnet.py` for a description of the
implementation.
An example usage of `neuralnet.py` is given in the `Usage.ipynb` notebook.
Alternatively you can open the whole code in Google Colab -> [here](https://colab.research.google.com/github/michabirklbauer/neuralnet/blob/master/neuralnet-colab.ipynb).
## Requirements
`neuralnet.py` is purely implemented in NumPy:
- [NumPy](https://numpy.org/): `pip install numpy`
To run the examples in the `Usage.ipynb` notebook locally please install the
requirements noted in `requirements.txt`:
- [Requirements](https://github.com/michabirklbauer/neuralnet/blob/master/requirements.txt): `pip install -r requirements.txt`
## Data
The following datasets are used in the examples:
- Multi-class classification: [MNIST](http://yann.lecun.com/exdb/mnist/index.html)
- Binary-class classification: [Breast Cancer Wisconsin (Diagnostic) Data Set](https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Diagnostic%29)
## License
- [MIT](https://github.com/michabirklbauer/neuralnet/blob/master/LICENSE)
## Contact
- [micha.birklbauer@gmail.com](mailto:micha.birklbauer@gmail.com)