This repository contains an in-depth exploration of the Gradient Descent algorithm with a focus on univariate or single-input variable linear regression. The lab includes detailed explanations, mathematical formulations, and code implementations.
- Algorithm Explanation: Understand the workings of Gradient Descent, exploring both its theoretical foundations and practical implementations.
- Cost Function Optimization: Witness how the cost function decreases iteratively, aiming to find the global minima using the Gradient Descent algorithm.
- Contour Plots: Visualize the optimization process through contour plots, gaining a better intuition of how Gradient Descent operates.
- Learning Rate Concept: Grasp the concept of the learning rate and learn how to judiciously choose it for a smooth convergence of the algorithm.
This lab notebook is adapted from the Machine Learning Specialization course by Andrew Ng on Coursera. It is highly recommended to refer to the original course for a comprehensive understanding of the material.