hi friends! if you'd like to sign up for the Aleph 0 math / machine learning newsletter, fill out the form here: forms.gle/Rt1f5StAj3yZtakE6 the next video is going to be a math explainer video, so stay tuned!! 👀
Thanks! Do you have an opinion on category theory used in machine learning? I've been following Petar Velickovic' Categorical Cybernetics for a short while and wondering if it's pragmatic at all
1:47 In reality, one will use scikit-learn most of time because: 1. You will not have enough data for training neural nets. 2. Even if you have enough data for training neural nets, you need a baseline model (let's say logistic regression or random forests) for performance comparison. 3. scikit-learn is more useful for rapid prototyping.
Pitching in to say: make videos on whatever you want to make videos on. If this is what you want, go for it. I personally prefer the pure math stuff, so if you’d prefer to talk about that please keep at it :)
I think this video is the part one because Deep Learning is a branch of Machine learning. Also, learning these topics need the practical part: coding in notebooks, reading repositories, get the well known datasets and training some models.
The difference is quite blurry? How so? Non DL algorithms are well known and they are all algorithms that are not based on the artificial neuron analogy connected into a network.
For a few weeks i have been wondering How could I learn machine learning once my studies were over (at the end of the year). I could not have dreamt about a better video. Thank you
Hi there, Thank you so much for this amazing self-study guide! I have a request: Could you create a self-study guide video for Analysis and the prerequisites needed to learn it? I would greatly appreciate it. Thank you!!
I think Aleph 0 is more af an Algebraist and may not have the most experience in Analysis, but i can give you some recommendations if you want me to, at least for Analysis at the undergraduate level.
When they OpenAI scientists were studying how to train ChatGPT to learn machine learning, it was probably called "learning machine learning, machine learning machine learning" Btw I love your videos, keep up the good content 👍
Of course! Most of the packages allows you either generate random dataset or download classical datasets in one line. Also people inventet holy huggingface.
Hello could you please do a self studying guide on applied mathematics. I'm about to go into fourth year and would like to explore topics deeper beforehand. I'm really interested in dynamical systems/modeling and their applications in epidemiology and finance.
I think it requires a lot of computing to train a neural network. But how much computing power does it take to run a pre-trained neural network. ie: is the computer required to run a neural network cheap? Can I run a speech neural network inside a teddy bear without connecting to the internet?
It depends on the problem and method you choose to solve it. You could use nn with billion parameters or linear regression with two parameters is enough for your goal.
Why are the pure math elitists so pissed off in the comments 😂 There are still a lot of pure math topics in the backbone of ML and this is nothing close to the intense meat-riding of more mainstream AI/ML channels
If you have zero experience and math is not your strong suit. However you are a hard worker and good study what tech career is available to those that love computers. Whats the easiest to get into beside UI/UX. Thank you to everyone with answers or suggestions.
how much maths do i need to know in order to understand the arcitecture of the transformer model deeply, so i can build one my self without use pre trained models? Also is there anything else I have to know in order to understand how transformers work Considering Im a beginner
Good video bhai. You have good boxing technique here but remember to return your hand to your face so you don't get countered! I wish you the best of luck in your upcoming fight!!
Liked this channel more when it was just about barebones exposition of math than what it's becoming now. Culling my old subsctibed channels, so I guess this is goodbye.
@kjv35 I agree, pure math is just mental exercise, absolute abstraction, but the mathematical tools you as physicist use today once were pure math as well. Before becoming a mathematician I was enrolled in a physics major, but then I started to love more and more pure math while hating lab stuff and swapped over. I still like theorerical physics but much more the mathematical aspect, and would never work with it, to me it seems very frustating to develop theories you are not even capable of imagine how to proof. Like I said, there's nothing wrong with applied math, but for me it's just boring in the long term, as a curiosity it can be interesting but suddently becomes boring. I just love the freedom of thinking that pure abstract math provides. My brother is a physicist so I actually have some contact with applied science through his research.
@kjv35 What I find boring about theoretical physics is the general uncapability of proving its recent statements, it seems too abstract to be physics but too real to be math. But I've self-studied some of its topics for hobby, like QFT, String Theory and General Relativity (I know the main and original statements of QFT and GR were prooved). Quantum mechanics was mandatory at my bachelor curriculum also and my professor of Riemannian Geometry came from physics so he presented us the basic ideas of GR as an application.
@kjv35 ok, but particle physics is something able to be "prooven". Now, how the hell will we ever be able to collect experimental data from inside a Black Hole or from another universe? A thing I love in math is that we are able to unarguably proof any of our conjectures. Obviously Kurt Gödel kinda messed up the perfect world of pure math but in everyday pure math research things tend to follow some strict logic that leads to ultimate proofs.
@kjv35 but now I'm curious. What was your experience with pure math to be so harsh towards us? You called us elitists who don't care about real world problems but a physicist who studies entropy of black holes also don't care that much about problems of the real world, in the sense of human daily world, since you can argue that black holes really exists aside of pure math, but it doesn't actually mean anything practical to the daily planet Earth.
This channel has consistently had a theme of self-studying. It’s perfectly natural for the topics to change as the author explores new topics. And it’s not like it’s a massive change, this is still a very maths-y way to learn ML.
![The moment we stopped understanding AI [AlexNet]](http://i.ytimg.com/vi/UZDiGooFs54/mqdefault.jpg)
hi friends! if you'd like to sign up for the Aleph 0 math / machine learning newsletter, fill out the form here: forms.gle/Rt1f5StAj3yZtakE6
the next video is going to be a math explainer video, so stay tuned!! 👀
Can't wait really. Can I know what's your favourite field in mathematics?
Thanks! Do you have an opinion on category theory used in machine learning? I've been following Petar Velickovic' Categorical Cybernetics for a short while and wondering if it's pragmatic at all
Thanks!
1:47 In reality, one will use scikit-learn most of time because:
1. You will not have enough data for training neural nets.
2. Even if you have enough data for training neural nets, you need a baseline model (let's say logistic regression or random forests) for performance comparison.
3. scikit-learn is more useful for rapid prototyping.
Pitching in to say: make videos on whatever you want to make videos on. If this is what you want, go for it. I personally prefer the pure math stuff, so if you’d prefer to talk about that please keep at it :)
The goat is back when we needed him the most
For reinforcement learning the video series by Mutual Information is an absolute must!
The Bahen Math Library is so underrated! Glad to see someone else is taking out books there too.
I took so many notes on the resources, books and videos you shared. Thank you! Cant wait to see more
What are you doing in life btw ? Are you a student, or working ?
Michael Nielson is one of the Greats!!!
I think this video is the part one because Deep Learning is a branch of Machine learning. Also, learning these topics need the practical part: coding in notebooks, reading repositories, get the well known datasets and training some models.
Shouldn't this rather be a self-study guide for deep learning rather than machine learning? (Although nowadays the difference is quite blurry)
Correct but here always will be difference. Non neural methods will exist and develope.
The difference is quite blurry? How so? Non DL algorithms are well known and they are all algorithms that are not based on the artificial neuron analogy connected into a network.
@@mindasb Yes but in day to day language when we say AI or ML we mean Deep Learning usually thats why the title is probably like that
I likd and learned machine learning; I didn't have a good teacher or experience -- I would like to start all over again
I just want to let you know how much I admire your videos! And I just realised you featured in "Shades Of Varali" by IndianRaga. Absolutely loved it!
For a few weeks i have been wondering How could I learn machine learning once my studies were over (at the end of the year). I could not have dreamt about a better video. Thank you
I really enjoyed the topic of this video, hope you make more on many different subjects in math physics and computer science
Hi there,
Thank you so much for this amazing self-study guide! I have a request: Could you create a self-study guide video for Analysis and the prerequisites needed to learn it? I would greatly appreciate it.
Thank you!!
Yes!
I think Aleph 0 is more af an Algebraist and may not have the most experience in Analysis, but i can give you some recommendations if you want me to, at least for Analysis at the undergraduate level.
@@red1bk190 Yes, this would be extremely helpful. Thank You!
When they OpenAI scientists were studying how to train ChatGPT to learn machine learning, it was probably called "learning machine learning, machine learning machine learning"
Btw I love your videos, keep up the good content 👍
Thanks for this video! I’m actually really curious how machine learning might be used to search for more efficient algorithms
Awesome 🤩 thank you ♥️
PRML is the first book people should read, no question
Many thanks !
great video, thanks a lot!
really liked the video, nice!!
A video on exotic spheres would be nice
thanks for the nice video and the literature list. perfect 🙂
Seems like for learning this the difficult part is obtaining the datasets for training
maybe there are online repositories
Of course! Most of the packages allows you either generate random dataset or download classical datasets in one line. Also people inventet holy huggingface.
Hello could you please do a self studying guide on applied mathematics. I'm about to go into fourth year and would like to explore topics deeper beforehand. I'm really interested in dynamical systems/modeling and their applications in epidemiology and finance.
What car do you have? It looks really sleek and clean. If it’s a Tesla could you specify which model? Thanks.
Sir please provide lectures on sieve theory
I think it requires a lot of computing to train a neural network. But how much computing power does it take to run a pre-trained neural network.
ie: is the computer required to run a neural network cheap? Can I run a speech neural network inside a teddy bear without connecting to the internet?
It depends on the problem and method you choose to solve it. You could use nn with billion parameters or linear regression with two parameters is enough for your goal.
Why are the pure math elitists so pissed off in the comments 😂
There are still a lot of pure math topics in the backbone of ML and this is nothing close to the intense meat-riding of more mainstream AI/ML channels
How much computing power do I need?
Put more videos pleaseee
Dang, I'm really looking forward to getting into a Data Science masters now
If you have zero experience and math is not your strong suit. However you are a hard worker and good study what tech career is available to those that love computers. Whats the easiest to get into beside UI/UX. Thank you to everyone with answers or suggestions.
only one prereq. it's easy! math
awesome video
how much maths do i need to know in order to understand the arcitecture of the transformer model deeply, so i can build one my self without use pre trained models?
Also is there anything else I have to know in order to understand how transformers work Considering Im a beginner
Just basic linear algebra and calculus
Wait, this isn’t LeaF.
It's funny he specifically doesn't mention 3b1b's videos on ML, reckon they are bland
They are i deed insipid. 3b1b is for kids, not for men.
Good video bhai. You have good boxing technique here but remember to return your hand to your face so you don't get countered! I wish you the best of luck in your upcoming fight!!
But I'm not a machine, how am I supposed to machine learning?
ML is about learning how to learn machine more effectively
Bahen 🤩?
When he talks about math, this channel was unique. Now he joined in red market and be one of them?
complete beginner?
skill issue
Bye, one of the best pure mathematics channels ever 😢. It was a good time.
He makes one video on a topic different from math and somehow you think it's no longer a math channel?
@@red1bk190 I fear it
Machine learning job role & AI contribution: th-cam.com/video/_ArcNNoaLww/w-d-xo.htmlsi=vzzYlQ5ZGHWG14GU
The only neural network you need is the one in your head
The last raise of nn occured when they win protein network in some tasks.
Okay, Luddite.
@kjv35at that time, that would’ve been true
Thought this was a math channel...
Tf do you think neural networks are? It's all calculus and linear algebra.
ML is all maths though?
@@halfsourlizard9319 they are applied math, the boring stuff
@@viniciuscillaand the money making stuff these days
@@viniciuscilladoes it really sound that boring to build a machine that can generate marvelous art just by typing a sentence?
Liked this channel more when it was just about barebones exposition of math than what it's becoming now. Culling my old subsctibed channels, so I guess this is goodbye.
Who tf asked? Cya
bro gave in to the ML hype 😭🙏 big loss for the TH-cam pure maths community
@kjv35there's nothing really wrong about applied mathematics, but is extremely boring
@kjv35 I agree, pure math is just mental exercise, absolute abstraction, but the mathematical tools you as physicist use today once were pure math as well. Before becoming a mathematician I was enrolled in a physics major, but then I started to love more and more pure math while hating lab stuff and swapped over. I still like theorerical physics but much more the mathematical aspect, and would never work with it, to me it seems very frustating to develop theories you are not even capable of imagine how to proof. Like I said, there's nothing wrong with applied math, but for me it's just boring in the long term, as a curiosity it can be interesting but suddently becomes boring. I just love the freedom of thinking that pure abstract math provides. My brother is a physicist so I actually have some contact with applied science through his research.
@kjv35 What I find boring about theoretical physics is the general uncapability of proving its recent statements, it seems too abstract to be physics but too real to be math. But I've self-studied some of its topics for hobby, like QFT, String Theory and General Relativity (I know the main and original statements of QFT and GR were prooved). Quantum mechanics was mandatory at my bachelor curriculum also and my professor of Riemannian Geometry came from physics so he presented us the basic ideas of GR as an application.
@kjv35 ok, but particle physics is something able to be "prooven". Now, how the hell will we ever be able to collect experimental data from inside a Black Hole or from another universe? A thing I love in math is that we are able to unarguably proof any of our conjectures. Obviously Kurt Gödel kinda messed up the perfect world of pure math but in everyday pure math research things tend to follow some strict logic that leads to ultimate proofs.
@kjv35 but now I'm curious. What was your experience with pure math to be so harsh towards us? You called us elitists who don't care about real world problems but a physicist who studies entropy of black holes also don't care that much about problems of the real world, in the sense of human daily world, since you can argue that black holes really exists aside of pure math, but it doesn't actually mean anything practical to the daily planet Earth.
Why the fuck do we need another generic machine learning and AI channel?
Im willing to bet you dont even know your pure math yourself. why would you be proud of closing yourself off of learning something new?
This channel has consistently had a theme of self-studying. It’s perfectly natural for the topics to change as the author explores new topics. And it’s not like it’s a massive change, this is still a very maths-y way to learn ML.
stay mad lmao, nobody asked for your opinion.
zzzzzzzzzzzzzz
Oh no, no more ML and AI it has become so boring 🥱
... Said no one ever.... In silicon valley
@@Horopter dude there is way more things in life than money, wake up
THAT'S THE VIDEO I'VE BEEN LOOKING FOR 🫶💪