I caught the AI flu – specifically the very virulent machine learning strain. It’s been on for several months now, and it’s getting worse by the day. At this point I think I should start infecting my readers.
Okay, okay jokes apart – welcome to my AI/ML Notes.
This is a new blog section which I intend to use to share technical materials on AI, starting with machine learning; and to also, once and for all, expunge all excuses my 18-year-old younger brother gives about why he doesn’t know much about the subject.
As the readers familiar with Machine Learning will know, there are three pillars to understanding the subject: 1) Mathematics (Linear Algebra, Multivariate Calculus…) 2) Computer programming, and 3) Statistics.
And, if it helps, you can always think of machine learning as advanced – or say modern – statistics for computer scientists.
My intention is to start from the barest scratch. To start from the mathematics pre-requisites, then I will cross over very gently into statistics, I will most likely skip any elaborate introductory programming tutorials, and then we will delve into various ML algorithms – and then begin to unpack them, break them into pieces, tear them apart, that kind of thing.
That being said, I can’t predict with certainty what I will do with this blog section in the future (nor can I predict anything whatsoever with certainty), but this is the plan for now.
When I am coding, expect to see me work with the sleek Jupyter notebook. Our programming language will be python, just because it is the most popular language amongst data engineers and data scientists. For data processing and handling, you will see me use pandas like crazy. For data visualization, I will work with matplotlib, seaborn (also based on matplotlib), and maybe plotly. I will use numpy and scipy for parametric and non-parametric statistics. Finally, for machine learning, I will use scikit-learn an awful lot.
In short, you will love it!
Again welcome to my AI notes.