// browse by topic

All Categories

Every post in the 30-Day AI Ramadan Series, organised by topic.
Find the exact concept you're studying — from ML foundations to transformers, LLMs, and prompt engineering.

← Back to Blog
🌙 Series progress
19 / 30 posts published
🧱

Foundations

How models learn, bias-variance, regularization, and the ML pipeline from data to deployment.

6 posts ▼
Day 1 What is Machine Learning? 11 min · Feb 19 → 🔒 Day 2 The ML Pipeline 10 min · Feb 20 → 🔒 Day 3 How Models Learn 12 min · Feb 21 → 🔒 Day 9 Bias, Variance & the Tradeoff 11 min · Feb 27 → 🔒 Day 10 Regularization: L1, L2, Elastic Net & Dropout 11 min · Feb 28 → 🔒 Day 14 Feature Engineering & Selection 14 min · Mar 4 → 🔒
🤖

ML Models

Classical algorithms from first principles — intuition, math, and code for every model.

8 posts ▼
Day 4 Linear Regression 10 min · Feb 22 → 🔒 Day 5 Logistic Regression 10 min · Feb 23 → 🔒 Day 6 K-Nearest Neighbors 10 min · Feb 24 → 🔒 Day 7 Naive Bayes 10 min · Feb 25 → 🔒 Day 8 Decision Trees 11 min · Feb 26 → 🔒 Day 11 Bagging & Random Forests 12 min · Mar 1 → 🔒 Day 12 Boosting: AdaBoost & Gradient Boosting 13 min · Mar 2 → 🔒 Day 13 XGBoost & LightGBM 13 min · Mar 3 → 🔒
🧠

Deep Learning

From neurons to networks — the bridge from classical ML to modern deep learning, backprop, and activations.

1 post ▼
Day 15 Neural Networks: From Logistic Regression to Deep Learning 23 min · Mar 5 → 🔒
👁️

Computer Vision

How machines see — CNNs, transfer learning for medical imaging, and real-time object detection.

3 posts ▼
Day 16 CNNs from Scratch 15 min · Mar 6 → 🔒 Day 17 Transfer Learning & Fine-Tuning 14 min · Mar 7 → 🔒 Day 18 Object Detection, YOLO & Segmentation 13 min · Mar 8 → 🔒
💬

NLP & Sequences

From raw text to meaning — tokenisation, RNNs, LSTMs, word embeddings, and how sequences are processed before transformers.

6 posts ▼
Day 19 NLP Fundamentals: Tokenisation, Bag-of-Words & TF-IDF 13 min · Mar 9 → 🔒 Day 20 Recurrent Neural Networks: The First Serious Attempt at Sequence Modelling 23 min · Mar 10 → 🔒 Day 21 GRU & LSTM: Teaching Networks to Remember 32 min · Mar 11 → 🔒 Day 22 Tokenization: How Text Becomes Numbers 20 min · Mar 12 → 🔒 Day 23 Word Embeddings: Word2Vec, GloVe & Sentence Transformers 35 min · Mar 13 → 🔒 Day 24 Attention & the Transformer Architecture 35 min · Mar 14 → 🔒
⚡

Transformers & LLMs

The architecture that changed everything — positional encodings, BERT vs GPT, and how large language models are built.

5 posts ▼
Day 25 Positional Encodings: Sinusoidal, RoPE & ALiBi 28 min · Mar 15 → 🔒 Day 26 BERT vs GPT: Encoders, Decoders & What They're For 25 min · Mar 16 → 🔒 Day 27 Tokenization Deep Dive: BPE, WordPiece & SentencePiece 22 min · Mar 17 → 🔒 Day 28 Fine-Tuning LLMs: Full, LoRA & QLoRA 26 min · Mar 18 → 🔒 Day 29 RAG Part 1: Retrieval-Augmented Generation Pipeline 28 min · Mar 19 → 🔒
🛠️

LLM Applications

Putting LLMs to work — prompt engineering from zero-shot to injection attacks, and understanding model limitations.

1 post ▼
Day 30 Prompt Engineering: Zero-Shot to Injection 25 min · Mar 20 → 🔒