Neural networks API for learning and practicing concepts presented in Andrew Ng's Coursera Deep Learning specialization courses. Implements backpropagation, mini batch gradient descent, RMSProp, Adam, regularization, and more. Written in Python.
The API is designed for learning how to implement deep neural networks from scratch and be able to quicky experiment and tune hyper parameters for binary classification, multiclass classification, and regression.
The neural network implementation is in DNN.py. To test/experiment start with test.py. The 3 datasets I've used for testing are all available on Kaggle.com