Free Big Data Education: A Data Science Perspective | Hacker News Reader

Free Big Data Education: A Data Science Perspective

bigdatarepublic.com

42 pointsAnon847 comments

> These free courses (some offer certifications) offer an excellent path toward obtaining the requisite background for becoming a data scientist. I’ve put together a BDR Data Science “pseudo degree program” for you to follow.

Here's my question as a have been thinking about pivoting into Big Data recently. I have a non-technical BA degree, but taught myself programming and have worked as a Software Engineer, Sr Software Engineer and Lead Engineer at a variety of startups. Since I dont have the math background I have been taking classes on Coursera in math/data science etc.

But I am torn on whether I need a MS degree in Applied Math/CS/Statistics etc. What is recommended? I have already read many blog posts/quora etc on the subject.

Also, do people compete on Kaggle etc to get their skills up?

These Free Big Data learning materials are great, but all the job postings for these positions want graduate level math capability, which makes sense. Whats the best way to jump int this?

You don't need graduate level math, but if you want to use machine learning it's basically mandatory to have a solid understanding up to calculus, linear algebra, and probability/statistics. At least if you want to understand the underlying algorithms, which in my opinion is essential to being a good data scientist.

I did a masters in machine learning/computer science, but I think I could have learned a lot of the stuff on my own. The value of the masters was in projects, interaction with professors/other students, and the ability to do research (which I think is very underrated). FYI: a lot of jobs will discriminate against people without technical degrees and graduate degrees. Independent projects or relevant work experience will help.

My career predates kaggle, but I did do a machine learning competition to practice and apply my knowledge. Winning these will look good on a resume, but only to a point: there's a lot more to being a data scientist than what these competitions test.

> FYI: a lot of jobs will discriminate against people without technical degrees and graduate degrees.

Thanks for the info. Thats my dilemma I guess. Leveraging free online resources can only take you so far. I guess my assumption was that I needed to get a masters and I was wondering which field made the most sense: Applied Math / Stats / CS. At this point it seems like CS would be the way to go.

CS would give you the most bang-for-your-buck, especially a program that can let you specialize in machine learning.

You may be able to leverage your software engineering positions to skip an additional degree. I've heard people argue that data scientists are software engineers with additional specialized knowledge, which I think is largely true.

> You don't need graduate level math, but if you want to use machine learning it's basically mandatory to have a solid understanding up to calculus, linear algebra, and probability/statistics. At least if you want to understand the underlying algorithms, which in my opinion is essential to being a good data scientist.

Key word in that last phrase being good. There are, of course, companies which will take developers with little experience and try to mold them into machine learning experts without much support -- the end result being misguided application of techniques. But hey, it's a job...

You don't "need" an advanced degree, but you will definitely benefit from solid understanding of statistics.

Maybe my undergraduate institution failed mebut I don't feel that having taken linear algebra, multivariable calc, applied stats, and graduate probability over the summer that the PDF below contains readily accessible information to me. Does it require graduate linear algebra? Graduate multi-v? We're my courses not rigorous enough? Am just not smart enough? I graduated summa cum laude, so maybe I should be okay.

All I am saying that is that there seems to be a huge leap between having taken the prerequisites everyone says you should take and then seeing Cramer-Rao bounds on page 70.

http://alex.smola.org/drafts/thebook.pdf

Reply on news.ycombinator.com