Pinned Tweet
This tweet is about how I have studied ML and made it my profession. I'll share the resources I've used and the sequence of my study.
Straight to point
ML pre-requisites(maths) : Linear Algebra, Probability Theory, Calculus, Optimization Theory(optional), Information theory(optional)
Linear Algebra: Lecture course by Gilbert Strang
Probability theory: MIT 6.041 (it contains parts of Bayesian inference as well)
Calculus: your high school and college classes are enough
Once basic maths is done then we move to ML.
Classical ML : CS229. Either by Andrew NG or someone else. Follow their lecture notes and solve their problem sets.
Reference books for classical ML that I followed: PRML by Christopher bishop, Pattern Classification by Duda, Hart and Stork
After getting comfortable with classical ML we move to Deep Learning and everything else.
Deep Learning and Computer Vision: CS231n. Very good lecture and assignments
Reference book: Deep Learning by Ian Goodfellow. This is the best book on deep learning. I’ve read some chapters of it many many times. Beautiful maths and intuitions
MLOps: dvc, WandB, MLFlow
NLP: I just read hugging face blogs. I haven’t spent much time with classical NLP though.
Alignment/AI safety/AI explainability: Anthropic Blogs(I’m a noob in this, just started learning couple months ago)
Additionally:
Blogs: Lilian Weng(OpenAI)’s blogs, colah’s blogs
Additionally: arxiv. I read many papers from arxiv
Karas and Tensorflow blogs: for introductory code about modern deep learning frameworks
Competitions: Kaggle
Cloud compute. GCP/collab/Kaggle notebooks
PS: this is not a roadmap. Just what I followed till now and I find it quite structured. Even after 5 years I still find myself learning new stuff everyday.
Straight to point
ML pre-requisites(maths) : Linear Algebra, Probability Theory, Calculus, Optimization Theory(optional), Information theory(optional)
Linear Algebra: Lecture course by Gilbert Strang
Probability theory: MIT 6.041 (it contains parts of Bayesian inference as well)
Calculus: your high school and college classes are enough
Once basic maths is done then we move to ML.
Classical ML : CS229. Either by Andrew NG or someone else. Follow their lecture notes and solve their problem sets.
Reference books for classical ML that I followed: PRML by Christopher bishop, Pattern Classification by Duda, Hart and Stork
After getting comfortable with classical ML we move to Deep Learning and everything else.
Deep Learning and Computer Vision: CS231n. Very good lecture and assignments
Reference book: Deep Learning by Ian Goodfellow. This is the best book on deep learning. I’ve read some chapters of it many many times. Beautiful maths and intuitions
MLOps: dvc, WandB, MLFlow
NLP: I just read hugging face blogs. I haven’t spent much time with classical NLP though.
Alignment/AI safety/AI explainability: Anthropic Blogs(I’m a noob in this, just started learning couple months ago)
Additionally:
Blogs: Lilian Weng(OpenAI)’s blogs, colah’s blogs
Additionally: arxiv. I read many papers from arxiv
Karas and Tensorflow blogs: for introductory code about modern deep learning frameworks
Competitions: Kaggle
Cloud compute. GCP/collab/Kaggle notebooks
PS: this is not a roadmap. Just what I followed till now and I find it quite structured. Even after 5 years I still find myself learning new stuff everyday.
81
559
4,079
702,777
Saurabh Kumar retweeted
@SanketPanda10 No one sees more startups than I do - all around the world. Spent three weeks in India with 15 companies. Quite convinced about what is going on. Never been to a place where the VCs have a worse reputation.
18
21
629
45,885
Saurabh Kumar retweeted
Is "Indian nepotism" real? Maybe.
Immigrant-founded firms tend to employ a lot of coethnics—especially for groups that don't really know English. Chinese founders fill 45% of first hires with Chinese, Mexicans 31%, and Poles 27%.
Indians are at 21%, below the immigrant average.
Immigrant-founded firms tend to employ a lot of coethnics—especially for groups that don't really know English. Chinese founders fill 45% of first hires with Chinese, Mexicans 31%, and Poles 27%.
Indians are at 21%, below the immigrant average.
@zagrebbi @blancmontagnard Indian nepotism isn’t real, right?
124
315
2,455
117,815
How do we build trust ladder for memory?
AI writes to slack, to notion, to JIRA and then reads back from it, considering it the source of truth?
One misleading fact and it becomes impossible to spot it unless it's too late
Coding on the other can provide immediate feedback
AI writes to slack, to notion, to JIRA and then reads back from it, considering it the source of truth?
One misleading fact and it becomes impossible to spot it unless it's too late
Coding on the other can provide immediate feedback
2
0
4
690
> leaves Anthropic
> immediately starts slandering Opus
> immediately starts slandering Opus
@lydiahallie wait is it just me or is Opus 5.5 dumber
3
0
78
10,080
Saurabh Kumar retweeted
Once again, communication in Japanese is hell if you are autistic.
Everything is secretly a code for something else. Nothing is ever said directly - even if the meaning is immediately apparent to everyone "in the know".
Everything is secretly a code for something else. Nothing is ever said directly - even if the meaning is immediately apparent to everyone "in the know".
A colleague says 普通はメールで連絡しますよね (futsū wa mēru de renraku shimasu yo ne).
It sounds like a remark about how people usually do things.
Often it is a correction: you did it differently.
Reply ご指摘ありがとうございます (goshiteki arigatō gozaimasu). Then adapt.
44
429
6,614
181,881
Saurabh Kumar retweeted
Tunnel Boring Machines का पूरा ecosystem भारत में बन रहा है।
Design ➡️ Manufacturing ➡️ Maintenance
आत्मनिर्भर भारत 🇮🇳
Design ➡️ Manufacturing ➡️ Maintenance
आत्मनिर्भर भारत 🇮🇳
423
3,670
15,658
401,123
Saurabh Kumar retweeted
Being fearless, not timid; being smart, not slimy; being gentle, not rude; and being skillful, not callous. These are all signs of the Daivi Shakti arising in you, and that is the celebration of Dussehra.
#Vijayadashami
#Dussehra
#Vijayadashami
#Dussehra
49
587
1,182
24,681
>India isn't developed, it's developing, so it needs patriots, not parasites
Preach
Preach
I think what is actually needed is for Indian people to actually give a damn about their cities and fellow citizens.
Anybody using the "I pay taxes, I shouldn't have to do anything" excuse should go live in another country. India isn't developed, it's developing, so it needs patriots, not parasites. If this triggers you, it means you're part of the problem.
If you're not happy with the footpath (or a pothole, or anything else which is broken), fix it, or call someone to fix it, and don't give up until it's fixed. Be relentless. Be vocal. Be creative. Make it your mission to get that one thing fixed. Look at what Virendra (@Virendra0698) did by just calling the right people and being respectful (but also persistent). He and Arun Pai (@arunpaiblrwalks) along with the help of GBA and some wonderful volunteers turned an unofficial garbage dump into a pristine, beautiful footpath through sheer force of will.
x.com/Virendra0698/s…
2
39
1,065
9,971
"Is it still worth pursuing ML as a career"?
Honestly this might be the best time. But you've to be careful
Just like you can't approach software enineering like you used to 7 years ago you can't approach ML the same way as well
Fundamentsl like Linear Algebra, Probability and Calculus is always needed, but once that's done, you gotta pick up a niche and start building on the go
Machine learning basics? Start with MNIST
Computer Vision? Start with Yolo
NLP? Start with sentiment analysis with encoder models
Generation? Start with VAEs and GANs
Text generation? Start with GPTs
Content summarization? Start with BERT
The way I learnt ML 10 years ago and the way ML should be learnt right is different. Every other day, 100s of new research papers on a topic is being published; the scope and much more broader and tuning knobs are becoming infinite
Pick a niche, and get started
Honestly this might be the best time. But you've to be careful
Just like you can't approach software enineering like you used to 7 years ago you can't approach ML the same way as well
Fundamentsl like Linear Algebra, Probability and Calculus is always needed, but once that's done, you gotta pick up a niche and start building on the go
Machine learning basics? Start with MNIST
Computer Vision? Start with Yolo
NLP? Start with sentiment analysis with encoder models
Generation? Start with VAEs and GANs
Text generation? Start with GPTs
Content summarization? Start with BERT
The way I learnt ML 10 years ago and the way ML should be learnt right is different. Every other day, 100s of new research papers on a topic is being published; the scope and much more broader and tuning knobs are becoming infinite
Pick a niche, and get started
7
8
179
7,530
RT @drishtadyumn: Nikita Bier is responsible for the violent hate crimes against indian people in America.
0
357
0
73
keeping Euler below Ramanujan is an insult to the genius Euler was
Every mathematician in the world would likely keep Euler at the top
Every mathematician in the world would likely keep Euler at the top
Ranking of the greatest mathematicians of all time:
1. 🇮🇳 Srinivasa Ramanujan
2. 🇨🇭 Leonhard Euler
3. 🇩🇪 Carl Friedrich Gauss
4. 🏴 Isaac Newton
5. 🇬🇷 Archimedes
6. 🇬🇷 Euclid
7. 🇩🇪 Gottfried W. Leibniz
8. 🇬🇷 Pythagoras
9. 🇮🇳 Aryabhata
10. 🇩🇪 Bernhard Riemann
Source: thetoptens
71
19
623
97,125