@Krmsh1n5
Junior ML Engineer at NAIC. Building NLP and information retrieval systems for low-resource Azerbaijani. President of the UFAZ Data Science Club.
Notes, research and resources shared with the community.
A rigorous undergraduate classical mechanics textbook known for its unusually large collection of problems — ranging from straightforward to genuinely hard. Covers Newtonian mechanics, Lagrangians, normal modes, central
A structured 3-specialization path for anyone with basic Python and programming skills who wants to break into ML and data science properly. Follow in order. Step 1 — Mathematics for ML & Data Science [Coursera — DeepLea
The edX version of MIT's computational thinking courses, split into two parts. 6.00.1x covers Python fundamentals and algorithmic thinking; 6.00.2x goes deeper into data structures, stochastic thinking, and simulation. A solid alternative to the OCW version if you prefer a more structured format with graded assignments. Free to audit (full access to all materials). Verified certificate available for an additional fee if needed. [Enroll on edX](https://www.edx.org/xseries/mitx-computational-thinking-using-python)
edx.org/xseries/mitx-computational-thinking-using-pythonA comprehensive playlist covering graph theory and algorithms from scratch — DFS, BFS, Dijkstra, Bellman-Ford, Floyd-Warshall, minimum spanning trees, max flow, and more. Directly relevant to the **Network Algorithms course (L1-S2)** at UFAZ, which covers graph representations, routing problems, Prim, Ford-Fulkerson, Edmonds-Karp, Dinic, Dijkstra, Bellman-Ford, and matching algorithms. Watch this alongside or before that course. [Watch on YouTube](https://www.youtube.com/playlist?list=PLDV1Zeh2NRsDGO4--qE8yH72HFL1Km93P)
youtube.com/playlistA beginner-friendly overview of generative AI — how LLMs work, prompt engineering basics, and real-world applications. Pair with AI for Everyone as an entry point before moving into the ML or Deep Learning specializations. [Enroll on Coursera](https://www.coursera.org/learn/generative-ai-for-everyone)
coursera.org/learn/generative-ai-for-everyoneA non-technical introduction to AI — what it can and can't do, how ML projects work, and how to think about AI strategy. Start here if you're completely new to the field before jumping into any technical courses. [Enroll on Coursera](https://www.coursera.org/learn/ai-for-everyone)
coursera.org/learn/ai-for-everyoneGood platform for practicing English reading and listening. Worth using regularly to build consistency, but keep in mind these are general English materials — actual IELTS exam texts and listening tracks tend to be less complex than what you'll find here. For official IELTS preparation, pair this with the Cambridge IELTS books and the British Council / IDP practice materials.
engnovate.comengnovate.comThe official textbook companion to MIT's 6.100L course. Covers computational thinking, Python programming, algorithms, data structures, and basic statistics — written by John Guttag, one of MIT's core CS educators. Worked through this alongside my internship at NAIC. More structured than the lecture slides alone — worth having open while going through the OCW course.
mitpress.mit.edu/9780262529624/introduction-to-computation-and-programming-using-python/MIT's official introductory CS and Python course, freely available on OpenCourseWare. Covers Python fundamentals, computational thinking, algorithms, recursion, data structures, and object-oriented programming — with full lecture slides, problem sets, and exams included. Went through this during my internship at NAIC. Solid foundation before jumping into anything ML-related.
ocw.mit.edu/courses/6-100l-introduction-to-cs-and-programming-using-python-fall-2022/Best math and ML intuition channel on YouTube. Covers linear algebra, calculus, neural networks, and transformers with unmatched visual clarity. Essential before or alongside any serious ML coursework.
youtube.com/@3blue1brown