Honesty just work through a math book, you will be able to read math in the ML domain pretty easy. I read "Mathematics for Machine Learning", it was a struggle for me, but taught me a lot of very useful skills.
@deeplearningexplained2 күн бұрын
Nice, will give it a read thanks for the recommendation!
@amunif_11 күн бұрын
I really wish there were courses in CS master’s degrees, teaching how to decipher the math in AI research papers
@deeplearningexplained11 күн бұрын
Yeah, that would have been helpful haha. However I had a cool course during my PhD in which every week we were reviewing a computational neuroscience paper. It was cool because we were digging into the code + we had a lecture with a similar style I adopted in my channel. It really helped see behind the veil of the papers method section!
@alikin9 күн бұрын
@@deeplearningexplained link?
@jerahmeelsangil2477 күн бұрын
Yeah, in Italy by the completion of bachelor degree in Computer Engineering you are in condition to read, understand and in some cases write papers atleast published in ARXIV
@IngramSnake6 күн бұрын
@@jerahmeelsangil247that’s cool but do they actually teach you how to do each of those things before requiring you to understand them? I feel this is much of the problem: there’s an element of show-off that keeps things closed off. 😂 this video is amazing ❤
@dylanhafner76086 күн бұрын
You shouldn’t be trying to “decipher” it…. You should actually know math
@Samuel193569 күн бұрын
Saw a random screenshot about this video on twitter, so glad I came to watch, thanks for the insights!
@deeplearningexplained9 күн бұрын
Glad it was useful Samuel!
@maahipatel58276 күн бұрын
⁰⁰0@@deeplearningexplained
@Antoniothescientist6 күн бұрын
As an AI/ML practitioner with no proper math education, I find this video very helpful for understanding the complexity of the algorithms and ensuring proper implementation for my use case. Would love to see more content like this!
@deeplearningexplained6 күн бұрын
Glad it was helpful, do let me know if you have topic requests!
@AlexsandroPessoa-m9x5 күн бұрын
Sincerely, after taking Calculus 3, 4, and Numerical in college, it feels like a trauma that will last for the rest of my life. Every time I use a gradient, I remember having to calculate it using only my paper.
@deeplearningexplained5 күн бұрын
Haha, at least you have a deep understanding of the material which is essential to understand topics that build upon it. Worth the PTSD!
@sepro51355 күн бұрын
I dont do CS or ML, but am getting into advanced Lattice Bolzmann stuff for Fluid Simulation, where a lot more basic understanding Is required than here (obviously, as the video is intended for a wider audience) but it was great to see the steps I usually take being actually formalized and first reasoning myself through this particular problem, before watching you do it, which worked pretty good. Overall great video, especially for ‚beginners‘
@massithegame87533 күн бұрын
Very good explanation! You’re the Jon Snow of mathematics.😅
@deeplearningexplained3 күн бұрын
Haha thanks for the kind words!
@dub1618 күн бұрын
In IISc, any student from any dept. are not allowed to touch any course from Intelligent Systems pool/AI dept. unless you are done with Linear Algebra, Stochastic Models/Random Process and Optimization and Analysis course. No AI for you unless you are cracked in Math.
@deeplearningexplained8 күн бұрын
Those are great pre-requisite for undergraduate or graduate AI courses 👍
@Chadpritai8 күн бұрын
are you at IISc dub161?
@rahulmalik10832 күн бұрын
Thanks to my exposure to advanced macroecon, the formulas don't seem crazy.
@deeplearningexplained2 күн бұрын
The more exposed to math you are the easier it gets for sure!
@eldarzakirov55717 күн бұрын
As an alternative to paper, I may suggest to use eink tablet with screen 13.3" and with drawing support, e.g. Boox Max Lumi, which alliws to draw directly on pdf.
@deeplearningexplained7 күн бұрын
Ah good idea, I also heard great things from ReMarkable!
@seanoconnor19842 күн бұрын
Fast transforms have a matrix equivalent that you can view as a neural network weight matrix. And then have parametric activation functions as the adjustable part. 1000 times faster neural networks.
@deeplearningexplainedКүн бұрын
Cool, thanks for sharing!
@seanoconnor1984Күн бұрын
@@deeplearningexplained 'K. The fast Walsh Hadamard transform is a good choice.
@kshitijdesai24023 күн бұрын
Very insightful!
@deeplearningexplained2 күн бұрын
Glad it was! :)
@rastko6144 күн бұрын
This is gold.
@deeplearningexplained4 күн бұрын
Glad it was useful :)!
@martinsteinmayer35578 күн бұрын
Great video man! Very well explained!
@deeplearningexplained8 күн бұрын
Thanks, glad it was useful! Let me know if you have request for the next tutorial.
@Fleniken4 күн бұрын
1. What's your sketching software that you put screenshots into? 2. How did you know to look in the "Adam" paper for the missing formula, and how did you find it? 3. What papers should I prioritize reading if I want to become a research engineer. And should I try tinker with the papers concepts to try put out my own blogs/mini-papers to demonstrate on workshops / to potential employers?
@MahmoudSayed-hg8rb4 күн бұрын
The SW is microsoft whiteboard Also im interested in his answer to your 3rd question so plz someone @ me if he replies
@deeplearningexplained2 күн бұрын
For sure CC: @MahmoudSayed-hg8rb 1. It's TLDRAW, it's free over here: www.tldraw.com/ 2. I know to look into the Adam paper because they mentioned that phrase in the article "Note that only the last expression differs from vanilla Adam". So I followed the reference for Adam and then in the paper I followed the flow until I hit the algorithm section (as you saw it was pseudo-code, not formulas). 3. My two cents is to start out with the classical architecture or core discovery of the last decade in the specific field you are interested. Read them and reproduce the result gradually. These are great to start out because they already have been implemented in different ways in bigger software package (Pytorch, Tensorflow). So you won't feel too much alone. Once you are getting the hang of it you can start reading and tinker with more recent result. I would suggest setting up a Github Repo for these reproduction and work on them gradually. No need to reproduce 100% of all the result in a paper, but by gradually working through the most important one you will start to get a hang of how the authors were thinking while getting there result. Plus you will have a set of nice project to walkthrough with potential employers!
@MahmoudSayed-hg8rbКүн бұрын
@@deeplearningexplained Thanks for @ing me and thanks for your answer 🫡🫡
@MahmoudSayed-hg8rbКүн бұрын
@@deeplearningexplained Thanks for @ing me and thanks for the answer, really appreciated.
@conradgnad5 күн бұрын
that was great, you are legend! thank you so much!
@deeplearningexplained5 күн бұрын
I’m glad it helped!
@sitrakaforler86967 күн бұрын
woooow was a cool video man ! keep it up
@deeplearningexplained7 күн бұрын
Glad it was useful!
@lukamoz8 күн бұрын
Ok as coding/math enthusiast who is looking into ML, i have understanding of calc 1,2,3, some stats and L.algebra how long it takes you guys to read paper like this (30 pages) from top to bottom? and implement it. I know on KAGGLE there are torunaments and they tend to use reserach papers for solutions.
@deeplearningexplained8 күн бұрын
Implementing the idea behind QHM and QHAdam is very fast, less than 1h. This paper is also very straightforward since it’s well written. Reproducing all the result in this paper though can take more time (to set up the experiments). But generally, reproducing a paper main result can take anywhere from a few hours to a full month depending on the complexity and how much I know about that subfield.
@aaryanbhagat485211 күн бұрын
great explanation
@deeplearningexplained10 күн бұрын
I'm glad it was useful!
@leolacic94422 күн бұрын
It's finaly whole explanation. Can I to go on the relax?
@deeplearningexplained2 күн бұрын
Yes you can 👍
@pratiknapit849410 күн бұрын
what about harder stuff when they talk about data manifolds or proving the convergence of stochastic gradient descent?? That stuff is way too difficult unless you have taken graduate math courses after 4 years of undergrad maths
@deeplearningexplained10 күн бұрын
Great question! What you need to do is start in reverse, go from the intuition and figure out the path from the primitives. A manifold is named like this for a reason that make intuitive sense for people understanding the mechanism behind. What I would do is first look at the path from primitives to result from many people/educators. Then I would make sure I understand what we are starting with. Finally I would take a step by step approach just like we did in this video and go fetch the information I’m lacking externally. Knowing the math well sure help speed the process up, but you can still figure out complex topic like that no matter your level.
@pratiknapit849410 күн бұрын
@@deeplearningexplained thank you!
@amirs64728 күн бұрын
great, thanks for video
@deeplearningexplained8 күн бұрын
Glad you enjoyed!
@shahulrahman25167 күн бұрын
I have completed LA, Probability and ML course. Have not done DL. I want to learn transformers and LLM's to conduct research upon it. Can you give me some directions.
@deeplearningexplained6 күн бұрын
Andrej Karpathy content is absolutely awesome to get started right in transformers and LLM: kzbin.info/www/bejne/sJvOc4B8nbOdlckfeature=shared
@whoami68665 күн бұрын
You know nothing, Jon Snow... but deep learning?
@deeplearningexplained3 күн бұрын
Hahaha
@jakeaustria54458 күн бұрын
Thank You❤
@deeplearningexplained8 күн бұрын
You’re welcome!
@jaidansvevo4393 күн бұрын
What application do you use to list the main aspects of the paper?
@deeplearningexplained2 күн бұрын
It's TLDRAW: www.tldraw.com/ ! Great app and it's free!
@jaidansvevo4392 күн бұрын
@@deeplearningexplained Thanks. Appreciate it!
@fatihmustafatuglu2365 күн бұрын
which sketch program is this?
@deeplearningexplained5 күн бұрын
It’s TLDRAW, it’s free and really solid!
@luka.software8 күн бұрын
Do you have any paper recommendations for someone that is just getting started with DL?
@deeplearningexplained8 күн бұрын
What background knowledge do you have and what aspect of deep learning interest you most?
@luka.software8 күн бұрын
@@deeplearningexplained I have a bachelors in software engineering and a bit of experience using SAM. Don’t have a specific interest but the image generation models like MJ are cool to me.
@deeplearningexplained7 күн бұрын
Okay neat, if you have a general interest then I would recommend the Deep Learning book. It’s not a paper per se, but it’s written with a similar flow as research paper and has pretty good references to the literature. It’s accessible though, so start with that and whenever you see a result that catch your attention dive into the base research it reference. This way you get both the benefit of context and with the depth of deep learning research. Hope it helps!
@luka.software6 күн бұрын
@@deeplearningexplained thanks i’ll check it out!
@sinan_islam2 күн бұрын
Reading math notation is a huge obstacle for me.
@deeplearningexplained2 күн бұрын
Did the tips in the video help a bit?
@sinan_islamКүн бұрын
The video helped alot. Thank you!
@walterobi5358 күн бұрын
What app do you use to split the pdf in sections, and dragging them around. Noob haha
@deeplearningexplained8 күн бұрын
I take screenshot of them and then I paste them in the TLDRAW free app!
@walterobi5358 күн бұрын
@@deeplearningexplained thanks.
@drprince87667 күн бұрын
Any Udemy course.:D
@deeplearningexplained7 күн бұрын
On which topic?
@Chadpritai8 күн бұрын
nice yapcine
@deeplearningexplained7 күн бұрын
:)
@sidharthcs21108 күн бұрын
All i saw was some woodoo magic
@deeplearningexplained7 күн бұрын
Haha, which part felt like this?
@EkShunya10 күн бұрын
can u please please setup a discord community? 🙏🏾 if u need help on this lemme know
@deeplearningexplained10 күн бұрын
Hey there, it's already setup over here :) 📌 discord.com/invite/QpkxRbQBpf
@EkShunya10 күн бұрын
@@deeplearningexplained thank you :)
@achunaryan34183 күн бұрын
Learn deep learning math.
@deeplearningexplained3 күн бұрын
Nothing beat strong fundamentals that’s for sure!
@cedricharris-v2rКүн бұрын
Coo)l
@deeplearningexplained8 сағат бұрын
:)
@RalphVikchain6 күн бұрын
I didn't get anything!
@deeplearningexplained6 күн бұрын
Oh no, where did I lost you?
@dffhhfhdifh7 күн бұрын
simply go learn maths calculus statistics differential and then jump into ai.why you in AI when math statistics is basics of AI.
@BryWMac6 күн бұрын
Well I think most ML practitioners have just a CS degree which typically don’t require beyond calc 3 and Lin alg 1. It’s just the way it is :/
@kar-s67163 күн бұрын
Wtf was that thumbnail
@deeplearningexplained3 күн бұрын
Did my best haha
@DuckGia7 күн бұрын
Broken maths. Solely to tackle a trivial optimization but lacks fundamental analysis.
@deeplearningexplained7 күн бұрын
Hey, thanks for the feedback! How would you have ran this tutorial differently?
@imaspacecreature10 күн бұрын
No bullshit, I think in this "math" at times, but cannot even begin drawing a formula. 😂
@deeplearningexplained10 күн бұрын
Try to code it instead, it's much easier in my opinion than using formula to start out.
@imaspacecreature10 күн бұрын
@@deeplearningexplained Yes! This is it. I've actually come up with some pretty interesting algorithms. I think in algorithm, it's strange, but yes I prefer to code it, then I can make a formula for what is happening. Perhaps it's kind of like sheet music. Also I'm working on a Neurosymbolic PHP only model, it's doing pretty well so far.
@redwingbeast13963 күн бұрын
@@imaspacecreature thinking in algos. please teach me how to!!
@imaspacecreature2 күн бұрын
@@redwingbeast1396 a while ago when I was younger my cousin took me to Kyoto, while there he decided to give me a pop quiz. He asked "In Japan, what is the tallest mountain in Japan?". I immediately knew I had access to it, but couldn't draw the memory in that instant. I in that moment, thought to my self "what if I rearrange my memories and sort by letter?", I did and upon reaching "F", "Mount Fuji" popped up in my mind.