Skip to content

Latest commit

 

History

History
32 lines (18 loc) · 2.25 KB

README.md

File metadata and controls

32 lines (18 loc) · 2.25 KB

Stanford_ML_AndrewNG

This repository contains the content and programming assignments of popular ML course on coursera provided under the supervision of Stanford University, delivered by instructor Andrew NG.

I AM HIGHLY GRATEFUL TO Andrew NG Sir FOR THE EXCELLENT COURSE.:slightly_smiling_face:

Course:

Link of the course

This repository contains the lecture content for quick reference.

I have uploaded my solutions in this repository. However, the solutions for quizzes and assignments of every week are best available here: Link for solutions

Programming Assignments of the course are implemented in Python 3 and can be found here:

https://github.com/itsayushisaxena/ML-AndrewNG-Python-Implementation -- Solved by me

Name of Repo: ML_AndrewNG_Python_Implementation

What I learned:

  • During Week 1: Machine Learning Definition and its real-time applications, Supervised Learning( Regression, Classification and examples), Unsupervised Learning(Clustering as example), Linear Regression with one variable, Model Representation. Cost function (well-explained with intuititons), Contour plots, Parameter learning-(Gradient Descent, Gradient Descent for Linear Regression and its Intuition. Important topics of Linear Algebra.

  • During Week 2: Multivariate Linear Regression(Multiple features), Gradient Descent Algorithm for Multiple Variables, Feature Scaling, Learning Rate, Feature and polynomial regression, Normal equation, Normal Equation Noninvertibility. Octave Installation. Octave/Matlab tutorial: Basic Operations, Moving Data Around, Computing on Data, Plotting Data, Control Statements: for, while, if statement, Vectorization.

Week 3:Logistic Regression--Classification,Hypothesis Representatio, Decision Boundary,Cost function and gradient descent,Advanced Optimization, Multiclass Classification: One-vs-all, Regularisation,Problem of Overfitting, Regularised Linear Regression, Regularised Logistic Regression, Programming Assignment

Week 4: Neural Networks: Non-linear Hypothesis,Neurons and the brain, Model Representation, Applications, Multiclass Classification