Machine learning and AI fascinate me because they meet at the intersection of all of these. The more I learn about it, the more I realise there’s plenty more to learn. And it gets me excited.
Let's start by this question :
“I want to learn Machine Learning Where can I start?”
Here are a few questions a machine learning engineer has to ask themselves daily.
- Context — How can ML be used to help learn more about your problem?
- Data — Do you need more data? What form does it need to be in? What do you do when data is missing?
- Modeling — Which model should you use? Does it work too well on the data (overfitting)? Or why doesn’t it work very well (underfitting)?
- Production — How can you take your model to production? Should it be an online model or should it be updated at time intervals?
- Ongoing — What happens if your model breaks? How do you improve it with more data? Is there a better way of doing things?
There’s no right or wrong way to get into ML or AI (or anything else).
The beautiful thing about this field is we have access to some of the best technologies in the world, all we’ve got to do is learn how to use them.
You could begin by learning Python code (my favourite).
You could begin by studying calculus and statistics.
You could begin by learning about the philosophy of decision making.