Best short yet informative story about Data Science Journey ever to be found! 👏🏼👏🏼👏🏼👏🏼👏🏼 thanks!

Isn't Double Descent already proved the Bias-Variance Trade-off irrelevant?

bro starting off with image of person wrist deep into the backside of animal lmao

From someone that has (maybe) the majority of the math knowledge that you talked about, I can't emphasize on the importance of the python libraries that you talked about Pandas, Numpy and sklearn, we sometimes forget how important they are especially if you come from a theory based background. Also, If you have some knowledge gaps (especially in the hypothesis tests in stats) you'll have a big trouble trying to make good predictions and/or insights. Also, I want to make a point on the part when you talked about calculus, I think it's important to study not only derivatives of single variable function, but also for multivariable ones, because it's important , for example to understand from where the estimators formulas in multiple linear regression came from. Good advice.

Please bro give me advice because I'm not cs student 😢

Nice vid! What are the hardest things about being DS? I mean soft skills area I'm currently working as a BI analyst, and I struggle a lot with confidence, earning trust to my dashboards among colleagues, I see DS route as one way of my futher career development but all these communications just drains me out

You explain the main goal of minimising rss. Could you please make videos on other equations from statistics and linear algebra

Yeah, man. You know what? You're some sort of Didactics Super Sayan. Thanks for the video. Instant subscribe.

But the term “Variance” in the Bias-Variance tradeoff DOES represent variance! It is the variance of the model’s predictions, Var(f~(x)). As the training data X is a random variable, so is the learned model and the predictions it produces f~(X). The rough intepretation of the variance term would be that the model changes a lot based on the training data

Can you give me the file for this presentation?

When it comes to ML, I often get lost and here it is a game changer. Thank you for your guidance. I have saved a lot of time.

for those watching and reading - I never finished HS - I didnt attend Uni. I have been a paid programmer for almost 25 years now. I never had impostor syndrome, because I never had all the accolades you guys get before starting. Dont believe it - its WEAK thinking. Push those obtrusive thoughts out of your head and just do it. Its the difference between "doers" and "talkers" - "winners" and "losers" I work in AI/ML now - still no degree. I learn the maths I need at each stage.

I usually watch these kind of videos (where the guy is yapping some roadmap or something) in 2x. For this guy I switched to 0.75x (< 1) in the first 2 minutes of the video.

Seriously most people or training school claim 3 or 6 months to be ML engineer. Thats almost impossible for those without a STEM degree at least.

3:59 this is sadly not true. Will you build programs fast? Yes. Will the programs be fast? ABso-fucking-lutely-not. You will need data science concepts, *a lot* to make python fast, you will need to dive into cython, and probably even binary code, and build libraries in a low lvl language, that suit your project, in order to make anything workable in python. Numpy is great and people use python because of tmodules like numpy, whicih is built in C and Fortran (wrapped in C and then into Python). So, yeah, don't keep your hopes too high for this tip.

This video is very informative. Short but very precise.

best video on this topic 💯

I strongly disagree on your screenshot with comically obvious and redundant comments as an example of good documentation. Maybe it was necessary 50 years ago, when languages and compilers were not that great, but today it's just like using a horse for transportation. Writing the same thing as the code, only in improper language like English, is bad. It's acceptable as training wheels, but after that it just creates extra confusion and debt. Having a comment is like crying "wolf!", if every line has them, nobody will pay attention to them. It also enables bad naming and structuring practices, since it gives a false sense of clarity. I'd say that if you have an urge to comment something, probably you should rename your variable or extract a function, not just write a comment saying that your variable myCatIsGreat is in fact just an index.

how can i get the full image from 4:30?

something confused my mind now, if every one has his special needs in learning, so why do we all learn the same thing in school and university?

14:05 as a developer my PR review would be to remove those comments. Function descriptions are fine. Comments on very complex logic is also good. That is just repeating the code.

6:03 isn’t the opposite? with k=1 we have underfitting and with k=1000 we have overfitting

overfitting in really big NNs is a more or less solved problem if you also have enough compute. For details read "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets". All big models use this phenomenon.

step one: just start doing ml projects and learn in field like we are supposed to. seriously, if you wanna learn anything just go do it and stop being stuck in analysis paralysis.

That last part about building off tutorials is very real. I find that most of the youtube guides/tutorials are very basic and meant for beginners, but if you take something basic and implement your own ideas it can become a larger and larger project which helps a ton

You should always focus early on the fundamentals, regardless of which field are you studying, period

I learned all that and built projects to then discover than I need to to master cause am not coming from CS background 😶 but business. The video is awesome man but I think if u offer mentorship I should be interested to join u and try to work on a group. Am in process of enrolling into master of data science program so I am doing lots of extra miles at this point.

13:59 This is horrible! Documenting all lines of code means you create unreadible code :) Code should be self-explenatory and comments should help to understand main ideas, algorithm features and use cases and sometimes why it is written in this manner (optimization, special case, etc) :D

The 100th commenter, U are like the big bro who spoke the utmost truth . ❤🙇

Bro changed the thumbnail and I thought I lost this video lmao

Two Thumbs up! A true Masterpiece.

Great content and giving the comments of ppl, who apparently are from the field, I definitively will subscribe! I just finished my DS bootcamp, and right at the beginning I knew it was an illusion, I would be able to master the whole thing in 3-4 months (even if I am ok at statistics and math). BUT, the 4 months gave me a good overview of the whole. Now, I am going back and started again to recap and practice, starting with python and dataviz.

This was awesome!

The best❤🎉

I use SPSS for machine learning.

The timing of this video has been perfect. Subscribed!

Informative.

Wow! I've taken many machine learning courses to date, but his breakdown is spot on! So concise! 🎉👍 Great job. Do you have more?!

Valuable overvidw but the speed of ghe speech seems to be boosted like 3x..please talk slower

What algorithm do you use when the features are tokens and the predicted object is a category?

Which algorithm is incremental and continuous?

New universe is comming🎉

What a great video, i think this is the ultimate, watched multiple videos for marking out common points and recourse for my best learning process. thank you for making this! sub +1

I don't see any point in memorizing ML algorithms.

What’s your best recommendation to start learning Python? I want to dive in 30min-1 hour a night. Was thinking of doing “real Python” open to suggestions to do it like a genius move like your ML video Thanks!

Just JOINED your course Cant wait to be a ML expert in 3 weeks!❤

Great video, I will save it so I can rewatch it any time I need to remember how to become a ML expert.

Dude, you just made my concepts so clear in just 17 minutes. Now I know what to use for my application. Thank you very much! You are Amazing!!!

Where is the next video? We're all waiting for you oh good sir!

dude just saved the whole gen ):