A simple neural network written in Python used as an exercise to learn Python as well as gaining more insight in how to write a neural network. It learns to recognize handwritten digits in the MNIST dataset.
Using techniques explained in the Machine Learning course by Stanford University on Coursera.
Python3 is required to run Hermes.
- Clone the repository.
- Get the MNIST dataset in CSV format
- Install the requirements using
pip3 install -r requirements.txt - Run
./hermes.py -f /path/to/mnist.csv
Run ./hermes.py --help to see additional options.