91–100 of 182 posts
I'm in my 40s and I started a machine learning degree in Nov 2020, so it's been about 1.5 years for me till now. I am a slow learner and my recommendations may reflect the same. 1) Maths (precalculus and calculus) - I started with Khan Academy 10th grade onwards. I finished till grade 12 in a week. By this time I had gone through content elsewhere, so 1 week may (not) be enough. Regardless, Khan Academy app comes hig…
Earlier quoted context omitted.
Fwiw it is not necessary to throw your college scores to actually learn as well: they just feel orthogonal sometimes. You can do both!
It depends where you study and what courses you take / who teaches you. Sometimes the professor will drive a ferocious pace of instruction and assessment and you will simply not be able to meaningfully keep up unless you sacrifice the depth of your learning in exchange for getting everything done. I have been in that position and watched my grades tank. Then, a year later, I watched my peers struggle with follow-up m…
If I did it again, I would take the minimum of 12 units (3-4 classes)... assuming I could afford to stay in school for 6 years. At the time, I was racing to graduate and get a job.
I was a C student in high school. I never took a math class beyond basic algebra. I started from Khan Academy's first exercise when I was 33 years old. It seems silly looking back that I was solving problems on the number line as an adult. At that time, around 10 years ago, Khan Academy had excellent coverage through trigonometry and single variable calculus. Once I reached that point I went to my local community col…
I was an A+ student up to Sophomore year in HS. I downgraded to A or B+ student after I knew how much fun actual learning is. Before that, all I was doing was memorizing and practising heuristics to get A+. I actually started learning Science since 11th grade. I grew and grew. And my scores tanked. Got only 6.xx/10 in college as well. But no regrets. Learning Math properly gave me a super solid foundation to learn De…
Earlier quoted context omitted.
I was an A+ student up to Sophomore year in HS. I downgraded to A or B+ student after I knew how much fun actual learning is. Before that, all I was doing was memorizing and practising heuristics to get A+. I actually started learning Science since 11th grade. I grew and grew. And my scores tanked. Got only 6.xx/10 in college as well. But no regrets. Learning Math properly gave me a super solid foundation to learn De…
> Now I do my semi-dream job as a Deep Learning Research Engineer building actual products with Deep Learning. > I have a truly realistic chance of getting my dream job within the end of this calendar year. So what’s your dream job? :-)
Or any co/startup doing "deep tech" in the area of Deep Learning.
I am doing _applications of DL_ now, want to do actual DL.
My biggest struggle was skipping some of the basics and having to go back and re-learn after really struggling. But struggling helped in a way because then I really understood why X or Y solution didn’t work. If there’s anything i’d suggest, it’s that once you get some confidence in solving problems, try to approach new ones without looking through the entire lesson first, and that will help the actual way to solve the problem really stick. (And it’ll help you ask more focused questions!)
Earlier quoted context omitted.
I was an A+ student up to Sophomore year in HS. I downgraded to A or B+ student after I knew how much fun actual learning is. Before that, all I was doing was memorizing and practising heuristics to get A+. I actually started learning Science since 11th grade. I grew and grew. And my scores tanked. Got only 6.xx/10 in college as well. But no regrets. Learning Math properly gave me a super solid foundation to learn De…
Fwiw it is not necessary to throw your college scores to actually learn as well: they just feel orthogonal sometimes. You can do both!
Not if you have other interests!
I am a very cultural person (reading books, writing, playing music, etc.). I volunteer after natural disasters, too. And I also value interpersonal relationships with people I care about.
It felt bad in HS, but in college, I was mature enough to simply not care. (I also gained enough skills in the meantime to be certain that I won't ever starve.)
Earlier quoted context omitted.
I was an A+ student up to Sophomore year in HS. I downgraded to A or B+ student after I knew how much fun actual learning is. Before that, all I was doing was memorizing and practising heuristics to get A+. I actually started learning Science since 11th grade. I grew and grew. And my scores tanked. Got only 6.xx/10 in college as well. But no regrets. Learning Math properly gave me a super solid foundation to learn De…
> I actually started learning Science since 11th grade. what event caused this? was it specific material or a specific teach or approach?
One taught me about what rigor was. In so many ways.
Another taught me that there is another side of Math. The non-heuristic parts. The stuff where is there is reason, logic, etc.
Dad took a broadband connection, and watching YouTube became realistic. I got 3b1b, Numberphile, MIT OCW.
Edit: My discovery of Halliday, Resnick, Walker physics textbook and Feynman lectures also was helpful. It was mostly- the Internet.
You don't say how much you already know. Your first stop would be Khan Academy and knowing your gaps. Fill your gaps. Learn HS level Calculus, Linear Algebra, and Statistics. You will need more Calculus and Linear Algebra later. But not now. Then try studying "Machine Learning for Absolute Beginners" book. It not very mathy. Then just keep going through ML courses. Learn what you need on the way. The "way" of math ne…
Although both are rooted in statistics, Data Science or Data Mining and ML are very different fields even if they might share some concepts and methods. I did different courses for each in University. Data Science is concerned with extracting patterns from existing data. Like you have some papers for exam and you want to know if students cheated. Or you have the results from a poll about people hobbies, income etc an…
More than basic notations and explanatory parts of research papers, I never need even iota of Statistics.
When you need to learn something specific, like, say, KL divergence, if your math is solid, then you can pick it up in 10 minutes.
I prefer hardbound textbooks, because computers are a big source of distraction. But there are also lots of generally very good free and open-source textbooks you can find online.