MLFSMLFS

Table of Contents

Chapters

15 chapters across three parts, plus a bonus deep-dive on LLMs. Read in order, or jump anywhere.

Part 1 — Basic Brain Rewiring

Foundations

  1. 01How to Think in FlowchartsStep over vibes. Learn to think like a computer before you code like one.
  2. 02Math You Can't Ignore (Sorry, Bestie)Vectors, calculus, probability — the only three you actually need.
  3. 03The Algorithm is a Lazy GeniusSupervised vs unsupervised, loss functions, gradient descent — the soul of ML.

Part 2 — Core Machine Learning

Real S#!t Starts Here

  1. 04DIY Linear RegressionBaby's first model. Predict stuff with a straight line, from scratch.
  2. 05Classification: The Yes or No SagaSigmoid, logistic regression, decision boundaries.
  3. 06Decision Trees: The Judgmental AlgorithmA flowchart that learns. Gini, entropy, information gain.
  4. 07KNN: The Neighborhood WatchNo training, just vibes. You are the company you keep.
  5. 08Naive Bayes: Trust Issues but Make It StatisticalBuild a spam filter from probabilities and bold assumptions.
  6. 09Clustering: Group Therapy for DataK-Means, the elbow method, finding cliques in chaos.
  7. 10Intro to Neural Networks: Baby's First BrainPerceptrons, activations, forward + backprop, conquering XOR.

Part 3 — Let's Build Things

Projects & Fun Stuff

  1. 11ML Playground: Code Like You Mean ItSpotify popularity, tweet sentiment, mood-based snacks.
  2. 12When Your Model Screws UpOverfitting, underfitting, cross-validation, precision vs recall.
  3. 13From Scratch to SklearnEarn your library — refactor your hand-coded models into 3 lines.
  4. 14Ethics, Bias & Bullshit DetectorsYour model isn't neutral. Build it like a responsible adult.
  5. 15Final Boss: End-to-End ML ProjectPick a quest. Build the pipeline. Ship it to the world.

Bonus

LLMs & All Their Fun Magic

  1. 16LLMs and All Their Fun MagicFrom Attention Is All You Need to models that actually think. Tokens, embeddings, QKV, transformers, RLHF, sampling, KV caches, MoE, chain-of-thought, o1-style reasoning — the whole stack, from scratch.