Question about self-studying math for data mining/machine learning
I'm a web developer who graduated from a uni with a degree in IT. When I was a uni student, I took one data mining subject, from which I found DM/ML highly interesting. Even after I became a web developer, I'm still interested in it.
I'm very seriously thinking about applying for a PhD course of the field, hoping that I would be a scientist/researcher etc. However, my degree is not CS/Math/Data science, so I decided to prepare myself for it.
Recently I got a data mining textbook and teaching myself with it, but it's difficult for me to comprehend what the book says, mainly because it involves many mathematical terms which I don't know/remember.
Here is a list of math which I found from the book.
* Linear algebra (Used for cosine similarity)
* Statistics & probability (Used for covariance of numeric data etc. Maybe these are part of high school math)
* Chi-squared test (Used for analysing and processing data)
* Wavelet (Used for data processing)
I guess all of them are essential but I'm not 100% sure.
So, my question is, is it necessary to understand all of them above? (I think it is) And, do you know any other math which is necessary to comprehend data mining technologies (maybe machine learning too)?
Any advice would be appreciated!