A DeepRat Educative Lab Program
About the Program • Estructure • Route of Apprentice • 📘 Complete Syllabus • 🚀 Quick Start Guide
Building Intelligence is an open, structured, and hands-on educational program that walks you through the full journey of modern Artificial Intelligence — from traditional Machine Learning to advanced Generative Systems and AI Agents.
The project is inspired by the spirit of open education. Just like Python para Todos once opened a door for me, this program aims to open that same door for anyone eager to learn and build — no subscription, no GPU cost, no barrier.
All lessons are built in Jupyter Notebooks, designed for Google Colab Free Tier (GPU-compatible when needed), and focused on real, reproducible AI systems.
The program is divided into 15 modules, each containing multiple chapters with theoretical and practical content.
Each chapter includes:
leccion_teorica.md→ theory and conceptual background01_nombre.ipynb→ core interactive notebookejercicios.ipynb→ practice exercisessoluciones.ipynb→ guided solutionsREADME.md→ learning objectives, prerequisites, and references
Lessons are released weekly, following a continuous, progressive path.
Current module: 📘 Teaching Machines to Think — The Python Approach 1️⃣ How Machines Learn — The Language of Data 2️⃣ Drawing the First Line — Predicting with Simple Linear Regression
Upcoming releases: 🗓️ Every 7 days — new lessons and chapters published here.
| Phase | Focus | Modules |
|---|---|---|
| 1. Machine Learning Foundations | Core algorithms and supervised learning | 01–02 |
| 2. Deep Learning Architectures | Neural networks, TensorFlow, Keras, PyTorch | 03–06 |
| 3. Generative AI & LLMs | Transformers, fine-tuning, and large model design | 07–11 |
| 4. AI Agents & RAG Systems | Retrieval, context, and intelligent orchestration | 12–15 |
- Python 3.10+
- Jupyter Notebook / Google Colab
- Common ML/AI libraries:
numpy,pandas,scikit-learn,matplotlib,torch,tensorflow,transformers,langchain, etc. (Installation handled automatically in Colab notebooks.)
- Teach AI engineering through real, executable projects.
- Provide fully open access to high-quality, structured material.
- Bridge the gap between theory and system implementation.
- Empower self-learners, students, and professionals to build real systems, not just run demos.
Follow updates, new module releases, and open discussions on:
All educational content is released under MIT License. Notebooks, diagrams, and examples are free for learning and adaptation — with attribution.
“From models to minds — let’s make intelligence open again.” — Gonzalo Romero (DeepRat)