search

ZuzooVn / machine-learning-for-software-engineers

A complete daily plan for studying to become a machine learning engineer.
https://www.codementor.io/zuzoovn/how-i-plan-to-become-a-machine-learning-engineer-a4metbcuk
Creative Commons Attribution Share Alike 4.0 International
28.06k stars 6.2k forks source link

Can you take a look at my Machine Learning Map and let me know what you think? #50

Open michaelbasca opened 7 years ago

michaelbasca commented 7 years ago

Hi, I stumbled upon your github approaching the same question I've been asking. What math prerequisites are required to have a rigorous understanding of Machine Learning? I made a map with dependencies. Would you mind taking a look at it and sharing your thoughts?

pschragger commented 7 years ago

The prereqs are greater than just math. Looking at the [outline of machine learning](https://en.wikipedia.org/wiki/Outline_of_machine_learning) we need a great deal of algorithm design, optimization. I believe it may be more that to get started you need to be able to pick a method that best fits the expected solution space and available data. Therefore, the focus on the applicablity of methods should be the focus of the learning the math. So I would think the next step is to attempt to map the math clouds to ml methods. Then you will find out if there is a gap in your map.

michaelbasca commented 7 years ago

Thanks. That's a good idea. I'm not sure if you can really put a chronology of dependencies as you could do with the prerequisites. Maybe an undirected graph showing connections (for instance perceptron algorithm is closely related to gradient descent algorithm etc.)? I'll take a look.