@olliefirth_ by "he is staying" i just think he means that teta loves the club and doesnt intend to leave unless he is asked to do so. more of a warcry rather than something to worry about i guess.
This book alone can change your ML interview game๐
If you're serious about AI, ML, or landing top-tier roles... this book is DIFFERENT.
โข Real-world deep learning interview problems
โข Step-by-step solutions
โข Covers ML math, probability, CNNs, Bayesian DL & more
โข Designed for people who actually want to understand, not just memorize
This isnโt basic theory.
This is the kind of prep that makes you walk into interviews confident.
And Iโm giving it FREE to first 4500
How to get it :
1๏ธโฃ Follow me MUST (So i can dm you)
2๏ธโฃ Like this post
3๏ธโฃ Comment โDLโ
4๏ธโฃ RT to help others level up
If youโre preparing for ML interviews in 2026, this could literally change your trajectory.
No fluff. No gatekeeping.
Letโs build killers in AI. ๐๐ฅ
dima_wallhacks reacts to the tools a cheaters uses to cheat on FACEIT without being detectedโผ๏ธ
He plays just like very other legit FACEIT player๐
If you're preparing for interviews, apart from DSA, projects, and CS fundamentals, remember that some companies also ask puzzles. I was asked one in an SDE Intern interview, where I got rejected.
Here are some resources to help you ace such puzzles asked in interviews.
Huge computer science result:
A Tsinghua professor JUST discovered the fastest shortest path algorithm for graphs in 40yrs.
This improves on Turing award winner Tarjanโs O(m + nlogn) with Dijkstraโs, something every Computer Science student learns in college.
"Complete Maths Roadmap for Machine Learning "
There are 3 pillars for maths involved in Machine Learning -
1) Algebra
2) Probability Theory
3) Calculus
Open thread
1/3 ๐งต
๐ ๐ฎ๐๐ต๐ฒ๐บ๐ฎ๐๐ถ๐ฐ๐ฎ๐น ๐ง๐ต๐ฒ๐ผ๐ฟ๐ ๐ข๐ณ ๐๐ฒ๐ฒ๐ฝ ๐๐ฒ๐ฎ๐ฟ๐ป๐ถ๐ป๐ด
This book will help you to build an understanding of fundamental mathematical concepts in deep learning.
๐๐ผ๐๐ฒ๐ฟ๐:
- Foundations and Scope of Deep Learning
- Neural Network Architectures and Activation Functions
- Universal Approximation and Expressivity
- High-Dimensional Approximation Theory
- Optimization Algorithms and Training Dynamics
- Neural Tangent Kernel and Infinite-Width Limits
- Loss Landscape Geometry
- Function Space Properties of Neural Networks
- Statistical Learning and Generalization Theory
PDF attached in comment.