When I started my Machine Learning journey, no matter which website or forum I went to, everyone told me that I need to have a solid background in mathematics to become a Machine Learning practitioner. You can search on Google for yourself right now and you will get a long list of topics which are considered as pre-requisites for Machine Learning. This includes:
1. Linear Algebra
2. Multi-variate Calculus
3. Statistics
4. Optimization
5. Probability
Have I had not studied Mathematics during my graduation, I would have left right there. I didn't, and over time I understood that to start your Machine Learning journey you do not need to learn math at all!
Before you start asking the billion questions that is going through your mind right now, let me explain. There are 2 ways to approach Machine Learning; theory and hands-on. With the hands-on approach all you need a bit of programming exposure, the enthusiasm and the tenacity to learn a new subject, a good teacher, and you are good to go. You can learn how the basics of Machine Learning, how to create model in scikit-learn, test it, see if it is giving good results, and what to do if it is not without opening a single mathematics book. With the advent of AutoML, this has become even more easier. A Machine Learning Engineer, in their typical day at office, does not require mathematics even once.
Don't get me wrong. I am NOT saying that you do not need to understand mathematics for Machine Learning at all. What I am saying is that to start with Machine Learning, you do not need to understand math. However, over time, you will need to understand the concepts better as you start working on complex problems. For example, without understanding linear algebra you will not understand how and why you should use PCA, or how calculus helps in understanding how does backpropagation works. But these can wait. You can pick up these skills along the way, and that will not be a challenge at all with all the resources available for free on the internet to master them.
So, start learning today, and never give up!
