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.
Many of these Sindhi Hindus migrated to India from Pakistan only three months ago, others came from 2013 onwards
Two days ago, Jodhpur administration demolished their shanties, leaving them to sleep in open, fetch drinking water from 3 kms away, no shelter for their kids in this scorching heat
Sitting with them, my heart aches at the misery. But let’s be determined to help them rehabilitate. I am collecting as much info as possible 🙏
This is how you can prepare for the 4 Frontend interview rounds
JavaScript-based problem solving -> https://t.co/yFqkyzBn7o
Machine Coding -> https://t.co/Z55z0wOUIs
System Design -> https://t.co/qUZe8OxB5q
Web Fundamentals -> https://t.co/tepNZOq9KM
The only 5 links you need to understand the Transformer:
(1) https://t.co/LgVwHxeMYP Let's build GPT: from scratch, in code, spelled out by @karpathy
(2) https://t.co/i4hw1HoOM9 Attention Is All You Need explained by @ykilcher
(3) https://t.co/pzz5j9148p Illustrated Transformer by @jayalammar
(4) https://t.co/ULGyZgZLuU GPT in 60 Lines of NumPy by @jaykmody
(5) https://t.co/zjOYlYG779 - Generative AI Visualization by the Financial Times
How about a Machine Learning course that doesn't rely on libraries?
Well, this "no black box" ML course teaches you the algorithms from scratch.
You'll learn how they work by building projects like a drawing app, data visualizer, and more.
https://t.co/oU6tFP3EpX
Here, in full directly on Twitter, is "A Hackers' Guide to Language Models". This 90 minute tutorial is designed to be the one place I point coders at when they ask "hey, tell me everything I need to know about LLMs!"
It covers both @OpenAI models and open source ones in depth.
REACT FRONTEND INTERVIEW QUESTIONS😃
I compiled a comprehensive React interview questions; grouped by skill level: 🫂
Easy:
What is React and why is it popular?
Explain the virtual DOM and its significance in React.
What is JSX in React? How is it different from HTML?
How do you create a React component?
What is the purpose of the render method in a React component?
What is the significance of state in React?
What is a functional component in React?
How do you pass data from a parent component to a child component?
Explain the concept of props in React.
What is React's key principle for optimizing performance?
Medium:
What are controlled components in React?
What is the purpose of the useState hook in React?
How do you handle events in React?
Describe the component lifecycle methods in React.
Explain the difference between componentDidMount and useEffect.
What is Redux, and how does it work with React?
What is routing in React, and how can you implement it?
What is the significance of keys in React when rendering lists?
How do you make AJAX requests in React?
What is Redux Thunk, and why is it used?
Hard:
Describe the concept of context in React and how it can be useful.
Explain the purpose of the useReducer hook in React.
What are Higher Order Components (HOCs) in React?
What is server-side rendering (SSR) in React? Why is it beneficial?
Compare and contrast React's PureComponent and shouldComponentUpdate.
What is the Virtual DOM reconciliation process in React?
Explain the concept of code splitting in React.
What are React hooks, and why were they introduced?
Discuss the challenges and solutions related to performance optimization in React applications.
How does React Fiber work, and what improvements does it bring to React?
Familiarize yourself with these frequently used design patterns across different layers in distributed systems.
These patterns are very handy during a system design interview, as they present solutions to frequently occurring problems.
Read more: https://t.co/Yb6gB8ucvE
Some DSA questions asked in my IBM interview:
Reverse a stack using recursion.
Reverse level order traversal in spiral form.
Insertion in an N-ary tree.
Finding the shortest prime path.
Topological sort implementation.
Snake & ladder problem.
The two water jug problem.
Stanford has released Prof. Manning's NLP course for free (!!!) on Youtube if you are interested in diving deeper into NLP.
It starts with the very basic word2vec and expends to:
-> Domain adaptation for supervised sentiment
-> Retrieval augmented in-context learning
-> Advanced behavioral evaluation
-> Analysis methods
-> More NLP methods
Happy A.B.L <Always Be Learning> y'all!
https://t.co/7kGpLzyBdY
As the team grows, we are looking out for talented engineers across roles.
If you (or someone you know) is looking out for roles in Web (Next.js/React), Android, iOS, React Native, GoLang, Node.js, Machine Learning or DevOps, reach out to the team by sending an email to [email protected]
Come craft new digital experiences and set new records along the way!
I'm learning so much from @theprogrammerin , @kushal124 , @PracSharma , @championswimmer , @jiten , @akisaxena , @yerrapragada , @NikhilSoman@some_rohit , @duncanjriley, @rivuchakraborty and so many individuals I interact with every day.
Pro Tip: Include a short cover note in body of your email, attach your resume, and don't forget to mention the role you're applying for in the subject line.