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.

I booked a topmate meeting with this guy who is a Senior ML engineer in an MNC. I asked my doubts related to career in Al/ML. After the talk, I realised the realistic path to get into AI/ML is totally different than what most youtubers tell. Here's what he told me. 🧵 (Part-1)

How to realistically prepare for AI/ML? (told by a Senior ML Engineer at an MNC) with roadmap, PDF and links. ( Part-2 )

“Should I solve LeetCode-type problems if I want to become an MLE” The answer is absolutely yes. The E in MLE stands for engineering and that means having an exceptional problem solving and thinking skills. Leetcode/codeforces help you develop that caliber. Also, many companies ask coding questions in their preliminary rounds for an MLE role. So it’s always a good choice

The most underrated Youtuber in Problem Solving world: @CSwithMIK 🌟 I've been practicing problem-solving (DSA) for over 1.5 years, and no one has taught me how to approach problems better than him. Let's give hardworking creators the recognition they deserve! #DSA #Coding

Full-stack web development resources that can be truly helpful in creating projects and succeeding in interviews at top MNCs. Sharing Roadmap along with resources to get started with the same. A thread 🧵

Life is full of stress and you are stronger than that

Servlet JSP Hibernate working on a project, then moving towards Spring Boot. -😍🙌 #javadeveloper #Springboot

2k impressions on Fiverr gig in a single day. 😭🥶🫡

Know your worth folks, don’t let anybody come and disturb your life. Give your time to only the people who truly matter to you and who respect your time and feelings.

I need your honest feedback on his courses. anyone please.

be kind.

console.log("hey JavaScript ♥️");

Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it.

I looked up "tailwind css hitesh choudhay" and had the same reaction as you initially. But, after watching his 4-minute video, "tailwind css is just crap," my perspective completely changed. Cool headline, @Hiteshdotcom