Logistic Regression with a Neural Network Mindset

This project is an implementation of a logistic regression classifier to recognize cats. The implementation is done with a neural network mindset, which helps in understanding the intuitions about deep learning.

Table of Contents

• 1 - Packages
• 2 - Overview of the Problem set
  • Exercise 1
  • Exercise 2
• 3 - General Architecture of the learning algorithm
• 4 - Building the parts of our algorithm
  • 4.1 - Helper functions
    • Exercise 3 - sigmoid
  • 4.2 - Initializing parameters
    • Exercise 4 - initialize_with_zeros
  • 4.3 - Forward and Backward propagation
    • Exercise 5 - propagate
  • 4.4 - Optimization
    • Exercise 6 - optimize
    • Exercise 7 - predict
• 5 - Merge all functions into a model
  • Exercise 8 - model
• 6 - Further analysis (optional/ungraded exercise)
• 7 - Test with your own image (optional/ungraded exercise)

Installation

This project requires Python 3 and the following Python libraries installed:

• NumPy
• h5py
• matplotlib
• PIL
• scipy

To run the project, you also need to have software installed to run and execute a Jupyter Notebook.

Run

In a terminal or command window, navigate to the top-level project directory Logistic_Regression_with_a_Neural_Network_mindset/ (that contains this README), and run one of the following commands:

ipython notebook Logistic_Regression_with_a_Neural_Network_mindset.ipynb