Series

Machine Learning Fundamentals

This series breaks down complex mathematical theories and algorithms into simple, intuitive explanations with practical examples, making AI accessible to everyone from beginners to aspiring data scientists.

Deep Learning Optimizers: Deriving Momentum, RMSProp, and AdamW mathematically
Derive and implement modern deep learning optimizers (SGD, Momentum, RMSProp, and AdamW) from scratch in Python.
Jun 18, 202611 min read10
Calculus of Backpropagation: Mathematical Derivation from Scratch with Matrix Derivatives
Derive and implement the backpropagation algorithm from scratch in Python using raw matrix calculus.
Jun 18, 202610 min read26
Softmax Function Explained: From Raw Scores to Probabilities
Why every neural network classifier converts its raw output through exponential normalization before calling it a prediction
May 3, 202623 min read229
Dot Product in Machine Learning: The Engine Behind Similarity, Attention, and Neural Networks
From cosine similarity to scaled dot-product attention — how one operation powers modern AI
May 3, 202622 min read588
Transfer Learning Explained: Standing on the Shoulders of Pretrained Models
How modern AI skips millions of training hours by reusing pretrained knowledge — and when to freeze, fine-tune, or train from scratch
Apr 18, 202628 min read27
Attention Mechanism Explained: How Transformers Learn to Focus
From the query-key-value formulation to multi-head attention — the mechanism that made transformers dominate AI
Apr 18, 202625 min read20

Command Palette