Merge pull request #1 from michabirklbauer/develop

add implementation

README.md

@@ -1,2 +1,35 @@
-# neuralnet
-Neural Network Implementation in NumPy
+# 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/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
+
+- [[email protected]](mailto:[email protected])