So a while ago… well now a long time ago, I enrolled in one of the most widely know machine learning courses ever. It is taught by the 600 pound gorilla of the Machine learning world aka “Andrew Ng”. And is offered through the Coursera online learning platform and Stanford University. When I first bought the course I was just like: “lets do this !!! ” , then a week went by and I was like: “Wow this is actually pretty easy to understand”, which in turn lead to me to where I currently am. That is not working through the lectures, but writing this blog post. I really want to get that certificate, and uncover the mysteries and oddities of the machine learning (ML).
Therefor, I am going to be starting a new series of blog posts that summaries what I learn each week from the course. This way I do review of the material at the end of each week, as well as gain a better understanding of the matter by teaching it to you guys.
So far I have only competed the first week of the course. This was Introduction week, and covered the following topics:
- What is machine learning ?
- What is Supervised Learning ?
What is Un-supervised Learning ?
- Linear Regression with One Variable
- Model Representation
- Cost Function
- Parameter Learning
- Gradient Descent
- Gradient Descent for Linear Regression
- Linear Algebra Review
So far this class has been taught amazingly well by Andrew Ng. I wish all courses that involved abstract topics and math were taught this well.
In the coming week I will make two post for part 1 and part 2 of this series. See you then.