Welcome to AIby{Examples} 🚀

"What I cannot create, I do not understand."
— Richard Feynman

Traditional AI education is often polarized:

1. Shallow High-Level Overviews: Black-box tutorials that import a library (model.fit()) without explaining the mechanics under the hood.
2. Dense Academic Treatises: Heavy mathematical proofs and walls of equations that obscure practical intuition and real-world engineering constraints.

AIby{Examples} bridges this gap through active, first-principles construction. Every topic is taught through concrete examples, hand-drawn visual sketchnotes, step-by-step mathematical derivations, and runnable, zero-magic Python code.

---

The 6 Pillars of First-Principles Learning

Every article across our curriculum is structured around our 6-Stage First-Principles Framework:

graph TD
    A["1. Intuition & Mental Models"] --> B["2. Minimal Working Example (MWE)"]
    B --> C["3. Under the Hood & Math Rigor"]
    C --> D["4. Hands-On Implementation"]
    D --> E["5. Common Pitfalls & Debugging"]
    E --> F["6. Challenge & Playground"]
    
    style A fill:#2563eb,stroke:#3b82f6,color:#fff
    style B fill:#059669,stroke:#10b981,color:#fff
    style C fill:#d97706,stroke:#f59e0b,color:#fff
    style D fill:#7c3aed,stroke:#8b5cf6,color:#fff
    style E fill:#dc2626,stroke:#ef4444,color:#fff
    style F fill:#0891b2,stroke:#06b6d4,color:#fff

1. Intuition & Visual Mental Models 💡

Before introducing equations or syntax, we establish a crystal-clear mental model. We use visual sketchnotes and intuitive analogies to explain the fundamental problem a technique solves and why it was invented.

2. The Minimal Working Example (MWE) ⚡

We present the absolute smallest, self-contained Python snippet that demonstrates the core mechanism. Zero bloated dependencies, zero black-box magic. You can run it, see the output, and immediately verify the transformation.

3. Under the Hood: Mathematical First Principles 📐

We never skip the math, but we never present math in isolation. We break down the mathematical formulations—from gradient descent to self-attention matrices—with step-by-step arithmetic and tensor dimension tracking:

$\mathcal{L}(\theta) = -\frac{1}{N}\sum_{i=1}^N \Big[ y_i \log(\hat{y}_i) + (1-y_i)\log(1-\hat{y}_i) \Big]$

4. Hands-On Interactive Code 🛠️

We scale the minimal example into clean, modular, production-grade PyTorch and Python implementations. You see tensor shapes, broadcasting rules, vectorization tricks, and performance optimizations.

5. Common Pitfalls & Debugging ⚠️

Real engineering happens when things break. We highlight subtle bugs, exploding/vanishing gradients, data leakage, dimensional mismatches, and numerical instability, along with proven debugging strategies.

6. Active Exploration & Challenges 🎮

Each guide concludes with tangible challenges and parameter explorations designed to stretch your intuition: "What happens if you set the learning rate to 10.0? What happens if the batch size is 1?"

---

Curriculum Roadmap

Our curriculum takes you from foundational mathematical concepts to cutting-edge generative AI:

Module	Focus Area	Core Topics
01. Foundations	History, Linear Algebra, Calculus, Python	Perceptrons, Matrix Calculus, Vector Spaces
02. Classical ML	Regression, Trees, Ensembles, Clustering	Gradient Descent, Random Forests, SVMs, PCA
03. Deep Learning	Neural Networks, Backprop, Optimizers	Autograd from scratch, Adam, BatchNorm, ResNets
04. NLP & Sequence Models	RNNs, LSTMs, Transformers, Attention	Tokenization, Multi-Head Attention, BERT, GPT
05. Computer Vision	CNNs, Vision Transformers, Segmentation	Convolutions, YOLO, ViT, Diffusion Models
06. Generative AI & LLMs	Pretraining, SFT, RLHF, DPO, RAG	KV-Cache, LoRA, FlashAttention, LangGraph Agents

---

How to Get the Most Out of AIby{Examples}

1. Type the Code: Do not just read the snippets. Open a Python REPL, terminal, or Jupyter notebook and execute them.
2. Break Things: Change hyperparameters, alter tensor shapes, and observe how the loss functions or outputs respond.
3. Follow the Diagrams: High-resolution architecture diagrams and sketchnotes are provided for every foundational model.

---

Ready to Begin?

Start your journey with the very first foundational topic:

👉 Start with Topic 1: A Short History of AI