VOL.01 HUB VOL.02 PORTFOLIO
LIVE · BENGALURU EST. 2024
★ Lab / Quests / Q-02
Q-02

ML Foundations from First Principles

The fundamentals every MAANG interview tests — owned, not memorised

Preparing for senior ML/AI engineer interviews the way I build systems: from the ground up. Each foundational concept gets studied to intuition, then the math, then a mock interview to find where my understanding is shallow. The blog is the proof of work — and my own revision material.

2
Experiments
0
Achievements
0
Learnings
Th · Op
Elements
2026-06 → present
Timeline
☉ Name the mechanism. Don't describe around it.
1RgRAG0
2EmEmbed0
3RkRerank0
4EvEvals0
5ClCalibrate0
6BmBenchmark0
7MlMLOps0
8LtLatency0
9CsCost0
10ScScale0
11PrPrompts0
12SfSafety0
13DbDebug0
14NtNotes0
15ThTheory1
16OpOptimise1
★ EXPERIMENT TIMELINE · 2 ENTRIES
✓
EXP #005✓ Achievement
Bias-Variance: The U-Curve Everyone Cites and Few Can Diagnose
Anyone can label a model "overfit". The signal is reading it off two numbers, knowing which lever to pull first — and knowing exactly where the classical theory stops being true.
2026-06-078 min
Test error decomposes cleanly into bias, variance, and irreducible noise — and a model's failure mode can be diagnosed from the gap between training and validation error, then trea…
✓
EXP #006✓ Achievement
Optimisers: From SGD to Adam, One Fix at a Time
Every optimiser is a patch on the one before it. Learn the chain — momentum fixes zigzag, RMSprop fixes the dying learning rate, Adam fuses both — and you can derive any of them from memory.
2026-06-079 min
The optimiser family is not a list to memorise but a chain of fixes: each method addresses a specific failure of its predecessor, and Adam is exactly Momentum (direction) plus RMSp…