Machine Learning: Model Representation And Hypothesis
I have started doing Andrew Ng’s popular machine learning course on Coursera. Andrew Ng’s Machine Learning course is well-rated and stretches for about 3 months with roughly 5 hours of study every week. My favorite aspect is that there are no prerequisites (you don’t even need to know any programming language). After 3 months you will experience substantial growth in your knowledge. The course covers various supervised and unsupervised machine learning techniques, along with guidelines of when to apply each of them and what to do in case they don’t work.
The course was designed using MATLAB / OCTAVE, which I think was a wise choice. MATLAB / OCTAVE is the easiest language to implement and allows for a better understanding of the Machine Learning concepts. Once these concepts are learned, it’s relatively easy to apply them in any language you desire.
I had a little programming and stats knowledge before beginning the course. I have to admit that the course wasn’t easy for me but not extremely difficult. I would love to share my note with you. Over the next few weeks, I will explain each of the topics covered in the course along with some Python to demonstrate.
The first week of the course primarily focused on:
- Model Representation
- Cost Functions
