A simple Python machine learning application for reading images of digits.

Requirements

• Python 3.x
• NumPy
• CSV

Setup

1. Clone the repository.
2. Install the required packages:

   pip install numpy

Usage

1. Ensure the training data is available in the train.csv file.
2. Run the digit-recognizer.py script:

   python digit-recognizer.py

Functions

• softmax(a): Computes the softmax of the input array a.
• predict(X, W): Predicts the output using the input X and weights W.
• cost(T, Y): Computes the cost function.
• grad(Y, T, X): Computes the gradient of the cost function.
• classify(Y, T, X, W, epochs, learning_rate): Trains the logistic regression model.

License

This project is licensed under the MIT License.