Phase 0: Course Setup¶

⏱️ Quick Setup (5 minutes)¶

Ready to start coding immediately? Here’s the fastest way:

Fork & Clone: Click “Fork” → git clone https://github.com/YOUR-USERNAME/zero-to-ai.git
Install: Run ./install_dependencies.sh (uses UV - fastest!)
Start: jupyter notebook → Open any .ipynb file
Begin Learning: Read …/MASTER_STUDY_GUIDE.md, then choose the first phase for your track

Not ready? See detailed setup below.

🎯 Introduction¶

Welcome to Zero to AI! This comprehensive learning path will take you from Python basics to production-ready AI systems. This setup guide will ensure you have everything you need to begin your AI journey.

🤝 Join Our Learning Community¶

Before you begin, connect with other learners and get support:

💬 Discussions: GitHub Discussions
🐛 Issues: Found a bug or have a suggestion? Create an issue

🍴 Fork or Clone This Repository¶

Step 1: Fork the Repository (Recommended)¶

Forking creates your own copy where you can track progress and make changes:

Click the “Fork” button at the top-right of this page
This creates https://github.com/YOUR-USERNAME/zero-to-ai

Step 2: Clone Your Fork¶

# Clone your forked repository
git clone https://github.com/YOUR-USERNAME/zero-to-ai.git
cd zero-to-ai

# Add upstream remote (to sync with original repo)
git remote add upstream https://github.com/PavanMudigonda/zero-to-ai.git

Quick Clone Options¶

Full Clone (for complete learning)¶

git clone https://github.com/YOUR-USERNAME/zero-to-ai.git

Shallow Clone (faster, recent commits only)¶

git clone --depth 1 https://github.com/YOUR-USERNAME/zero-to-ai.git

Sparse Clone (specific sections only)¶

# Clone with minimal data
git clone --depth 1 --filter=blob:none --sparse https://github.com/YOUR-USERNAME/zero-to-ai.git
cd zero-to-ai

# Choose specific sections
git sparse-checkout set 02-data-science 06-neural-networks 11-prompt-engineering

🚀 Environment Setup¶

Option 1: Quick Setup with UV (Recommended - Fastest!)¶

# Install UV package manager (if not installed)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install all dependencies
./install_dependencies.sh

# Activate environment
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

Option 2: Conda Environment (Recommended for ML/Data Science)¶

# Create environment from environment.yml
conda env create -f environment.yml

# Activate environment
conda activate aiml-learning

Option 3: Traditional Python venv + pip¶

# Create virtual environment
python -m venv .venv

# Activate it
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

Verify Installation¶

# Check Python version (should be 3.9+)
python --version

# Verify key packages
python -c "import numpy, pandas, sklearn, torch; print('✅ All packages installed!')"

# Start Jupyter
jupyter notebook

🎓 What You’ll Need¶

Hardware Requirements¶

Component	Minimum	Recommended	Notes
RAM	8GB	16GB+	32GB for advanced topics
Storage	10GB free	50GB+ free	Large datasets & models
CPU	Any modern CPU	Multi-core (4+ cores)	Intel i5/AMD Ryzen or better
GPU	Optional	NVIDIA with CUDA	GTX 1060 or RTX 2060+
Internet	Stable connection	High-speed	For cloud options & downloads

Prerequisites¶

Python Knowledge: Basic understanding of Python (loops, functions, classes)
- New to Python? Start with 01-python/ section first
Mathematics: High school algebra (we’ll teach the rest!)
Time Commitment: 10-15 hours/week for 6-12 months
Hardware: Any modern computer (GPU helpful but not required initially)

Required Software¶

Python 3.9+ - Download here
Git - Download here
Jupyter Notebook - Installed via requirements.txt
VS Code (recommended) - Download here

Optional but Recommended¶

GitHub Account - For saving progress and collaboration
Google Colab Account - For free GPU access
Kaggle Account - For datasets and competitions

🌐 Cloud Development Options¶

GitHub Codespaces (Recommended for No-Setup Experience)¶

Go to your forked repository on GitHub
Click Code → Codespaces → Create codespace on main
Wait for the environment to build (first time takes ~5 minutes)
Start coding! Everything is pre-installed

Google Colab¶

Click
Each notebook can be opened directly in Colab
Free GPU access available

Replit¶

Click
Collaborative coding environment
Great for learning with others

Kaggle Kernels¶

Click
Create a new notebook, enable Internet, and clone this repo from GitHub inside the notebook
Access to free GPU/TPU
Large dataset library included

📂 Repository Structure Overview¶

zero-to-ai/
├── 📘 00-course-setup/        ⭐ START HERE - Setup & orientation
├── 📚 01-python/                Python fundamentals (if needed)
├── 📊 02-data-science/          NumPy, Pandas, Scikit-learn (278 notebooks!)
│   ├── 1-numpy-examples/       Array operations & data manipulation
│   ├── 2-pandas-examples/      DataFrames & analysis
│   ├── 3-data-science-examples/ Statistical analysis & visualization
│   ├── 4-matplotlib/           Plotting & charts
│   └── 5-scikit-learn/         Machine learning algorithms
├── 🔢 03-maths/                 Linear Algebra, Calculus, Statistics (40+ notebooks)
│   ├── foundational/           Core math topics
│   ├── mml-book/              Mathematics for Machine Learning
│   ├── islp-book/             Statistical learning with Python
│   ├── cs229-course/          Stanford ML course
│   └── advanced/ 🆕           Learning theory, optimization
├── 🔤 04-token/                 Tokenization (tiktoken, sentencepiece, HF)
├── 🎯 05-embeddings/            Word & sentence embeddings
├── 🧠 06-neural-networks/       Deep learning from scratch to Transformers
├── 💾 07-vector-databases/      Chroma, Qdrant, Weaviate, Milvus, pgvector
├── 🔍 08-rag/                   Retrieval-Augmented Generation
├── 🚀 09-mlops/                 Deployment, monitoring, optimization
├── 🎨 10-specializations/       AI Agents, Computer Vision, NLP
├── 💬 11-prompt-engineering/    Advanced prompting techniques
├── ⚙️ 12-llm-finetuning/        LoRA, QLoRA, PEFT
├── 🎭 13-multimodal/            Vision, Audio, Video AI
├── 🏠 14-local-llms/            Ollama & private AI
├── 🧪 15-ai-agents/             Autonomous AI systems
├── 📈 16-model-evaluation/      Model evaluation & metrics
├── 🔧 17-debugging-troubleshooting/ Troubleshooting & debugging
├── ⚡ 18-low-code-ai-tools/     No-code AI tools
├── 🛡️ 19-ai-safety-redteaming/ AI safety & red teaming
├── 📡 20-real-time-streaming/   Live AI applications
├── 📝 21-quizzes/               Knowledge assessments
├── 📖 22-references/            Research papers & resources
├── 🗂️ 23-glossary/             Terminology & definitions
├── 🧠 24-advanced-deep-learning/ Cutting-edge techniques
├── 🎯 25-reinforcement-learning/ Reinforcement learning
├── 📊 26-time-series-analysis/  Time series analysis
├── 🔬 27-causal-inference/      Causal inference
├── 🔨 28-practical-data-science/ Practical data science
└── 📚 scripts/                  Utility scripts & tools

🗺️ Your Learning Path¶

Phase 0: Setup & Prerequisites (You are here!)¶

✅ Complete this setup guide
✅ Review 23-glossary/GLOSSARY.md for terminology
✅ If new to Python, start with 01-python/

Phase 1: Foundations (Weeks 1-8)¶

Lesson 1: Python & Data Science - 278 notebooks
Lesson 2: Mathematics for ML - Linear algebra, calculus, stats

Phase 2: Core AI (Weeks 9-20)¶

Lesson 3-7: Tokenization → Embeddings → Neural Networks → Vector DBs → RAG

Phase 3: Advanced Topics (Weeks 21-32)¶

Lesson 8-13: MLOps → Specializations → Prompt Engineering → Fine-tuning → Multimodal → Local LLMs

📋 Next Steps¶

✅ Complete Setup: Ensure your environment is working
✅ Read the Checklist: Open checklist.md - your complete roadmap
✅ Start Learning: Begin with 23-glossary/GLOSSARY.md, then move to the first phase for your track
✅ Track Progress: Use python scripts/progress_tracker.py to monitor your journey
✅ Join Community: Connect with other learners for support

🆘 Troubleshooting¶

Common Issues¶

Issue	Solution
`ModuleNotFoundError`	Run `pip install -r requirements.txt` again
`Python not found`	Ensure Python 3.9+ is installed and in PATH
`Jupyter kernel not found`	Run `python -m ipykernel install --user`
`Import torch fails`	Install PyTorch: `pip install torch`
`Out of memory errors`	Use Google Colab for free GPU
`Git clone too slow`	Use shallow clone: `git clone --depth 1 ...`

Getting Help¶

Check troubleshooting.md for detailed solutions
Search GitHub Issues
Ask in Discussions

🎯 Verification Checklist¶

Before moving to Lesson 1, ensure:

Repository cloned/forked successfully
Python 3.9+ installed and accessible
Virtual environment created and activated
All dependencies installed (pip list shows numpy, pandas, sklearn, etc.)
Jupyter Notebook launches successfully
Can open and run a test notebook
Read checklist.md learning roadmap
Familiar with 23-glossary/GLOSSARY.md terms

🎓 Ready to Start?¶

Congratulations! 🎉 You’re all set up and ready to begin your AI journey!

Next Stop: Lesson 1: Python & Data Science →

📚 Additional Resources

Main README - Repository overview
Learning Checklist - Complete roadmap
Setup Guide - Detailed installation instructions
Contributing Guidelines - How to contribute
Code of Conduct - Community guidelines

Need Help? Open an issue or join our community!

Found this helpful? ⭐ Star this repo to support the project!