Open-source AI education built by a student, for students and learners worldwide.
Basic to Expert. Zero to Language Models. 64 lessons. 100% hands-on.
Quick Start • Student Guide • Exam Prep • LinkedIn • Support Project
This is an independent learning project, NOT official University of Auckland, material. Use responsibly and follow your institution's academic integrity policies. See Academic Integrity Policy for details.
A structured, hands-on learning path from basic arithmetic to complete language models. 64 lessons with runnable code, visualizations, and practical projects.
Perfect for:
- University students learning AI/ML
- Self-learners building AI skills
- Professionals upskilling in deep learning
- Anyone wanting to understand AI from first principles
| Level | Lessons | Duration | Best For |
|---|---|---|---|
| Basic (B01-B15) | 19 | 2-3 weeks | Foundations & core concepts |
| Intermediate (I01-I15) | 15 | 4-6 weeks | Advanced techniques |
| Advanced (A01-A15) | 15 | 6-8 weeks | Production systems |
| Expert (E01-E15) | 15 | 8-10 weeks | Research & innovation |
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # macOS/Linux
.venv\Scripts\activate # Windows
# Install dependencies
pip install tensorflow torch numpy matplotlib jupyterjupyter lab
# Open any notebook from Basic/ folderOr use Google Colab (no setup needed) - Click "Open in Colab" badge in any notebook.
AI/
├── Basic/ # 20 Lessons (B01-B15 + B01a, B05a, B05b, B05c, B10a) ✅
├── Intermediate/ # 15 Lessons (I01-I15) ✅
├── Advanced/ # 15 Lessons (A01-A15) ✅
├── Expert/ # 15 Lessons (E01-E15) ✅
├── application/ # Live demos & practical implementations
├── documentation/ # Guides & resources
└── landingpage/ # Landing page assets
Interactive demonstrations of AI concepts in action:
Interactive AI demos — playable in your browser
| Demo | Concept | Course | Course Page | Notebook | Link |
|---|---|---|---|---|---|
| Wumpus World | Symbolic Logic & Knowledge Representation | UoA-COMPSCI 713 | COMPSCI 713 – AI Fundamentals | — | Play Online |
| Mountain Explorer | Gradient Descent & Optimization | UoA-COMPSCI 714 | COMPSCI 714 – Neural Networks | B02 - Linear Regression · B05b - Training & Optimization | Play Online |
| Neural Network Trainer | Forward Propagation, Backpropagation & Gradient Descent | UoA-COMPSCI 714 | COMPSCI 714 – Neural Networks | B05 - Neural Network Fundamentals · B05a - Neural Networks Theory | Play Online |
| Data Preprocessing Studio | Missing Values, Feature Scaling, Encoding & Feature Engineering | UoA-COMPSCI 714 | COMPSCI 714 – Neural Networks | B06 - Data Preprocessing and Feature Engineering | Play Online |
| PyTorch Assignment Practice | Tabular MLP, BCEWithLogitsLoss, Optuna, FashionMNIST CNN, Saliency Maps | UoA-COMPSCI 714 | COMPSCI 714 – Neural Networks | B05c - MLP on Tabular Data with PyTorch | — |
| KG Playground | RDF Triples, Knowledge Graphs, RAG & Conflict Detection | UoA-COMPSCI 713 | COMPSCI 713 – AI Fundamentals | A03 - Retrieval-Augmented Generation | Play Online |
| CNN Explorer | Convolution, Pooling, Feature Maps, Architecture & Playground | UoA-COMPSCI 714 | COMPSCI 714 – Neural Networks | B09 - CNNs | Play Online |
| Transformer Explorer | Self-Attention, Multi-Head Attention, Q/K/V & Architecture | UoA-COMPSCI 714 | COMPSCI 714 – Neural Networks | B11 - Attention & Transformers | Play Online |
| BPE Explorer | Byte Pair Encoding, Tokenization, Subwords & Vocabulary | UoA-COMPSCI 714 | COMPSCI 714 – Neural Networks | B12 - BPE | Play Online |
View All Games • Explore the application/ folder for source code and deployment guides.
| Course | Focus | Examples |
|---|---|---|
| COMPSCI 713 | AI Fundamentals | Symbolic Logic, Knowledge Representation, Search, RL, Sustainability |
| COMPSCI 714 | Neural Networks | Networks, Gradient Descent, CNNs, Attention |
| COMPSCI 762 | ML Foundations | Regression, Classification, Tuning |
| COMPSCI 703 | Generalising AI | Transfer Learning, Domain Adaptation |
| COMPSYS 721 | Deep Learning | Detection, Time Series, NLP, GANs |
COMPSCI 713 Complete Guide · COMPSCI 714 Complete Guide
- Before lectures: Review relevant Basic lessons
- During semester: Build practical projects from examples
- For assignments: Use as reference, implement your own
- For exams: Review all concepts in relevant lessons
| Document | Purpose |
|---|---|
| Student Guide | Course mapping, semester planning, study strategies |
| Exam Prep Guide | Exam strategies, practice problems, concept review |
| COMPSCI 713 Complete Guide | AI Fundamentals course guide with week-by-week lesson alignment |
| COMPSCI 714 Complete Guide | Neural network course guide with lecture alignment |
| Documentation Index | Complete guide to all documentation |
| Academic Integrity | Responsible use guidelines |
- Symbolic logic & first-order logic
- Tensors & linear algebra
- Linear regression & gradient descent
- Binary & multi-class classification
- Neural networks from scratch
- Training & optimization theory (COMPSCI 714)
- Data preprocessing & evaluation
- Regularization & overfitting
- CNNs, RNNs, Transformers
- Tokenization & language models
- Advanced optimization & regularization
- Transfer learning & domain adaptation
- Object detection & segmentation
- Seq2seq & advanced transformers
- Hyperparameter tuning & AutoML
- Generative models (VAEs, GANs)
- MLOps & deployment
- Fine-tuning LLMs
- Prompt engineering & RAG
- Vision-language models
- Distributed training
- Mixed precision & inference optimization
- ML pipelines & monitoring
- Responsible AI
- Reading & implementing research papers
- Neural architecture search
- Meta-learning & few-shot learning
- Deep reinforcement learning
- RLHF & alignment
- Federated learning
- Cutting-edge research
Beginner: Sentiment analysis, image classifier, text generator, spam detector, digit recognition
Intermediate: Medical image analysis, chatbot, stock predictor, document summarizer, multi-label classification
Advanced: RAG system, domain-specific LLM, multi-modal search, code reviewer, real-time detection
Research: Novel architecture, paper reproduction, bias detection, model compression, federated learning
✅ Appropriate Use:
- Learning concepts and understanding implementations
- Preparing for lectures and exams
- Using as inspiration for original projects
- Understanding different approaches
❌ Inappropriate Use:
- Copying code for assignments without understanding
- Submitting repository code as your own work
- Using during closed-book assessments
- Violating your institution's policies
Full Academic Integrity Policy
Contributions welcome! See Contributing Guide for details.
- Questions? Check Documentation Index
- Issues? Open a GitHub issue
- Suggestions? Submit a pull request
- Connect: LinkedIn
- Discord: Join the discussion
This repository represents hundreds of hours of work to make AI education accessible to everyone. If you find it helpful, consider supporting its continued development!
Every contribution, no matter how small, makes a difference!
Created by a student pursuing a Master of Artificial Intelligence at the University of Auckland.
Why this exists: To make quality AI education accessible to everyone, combining theory with practical implementations.
MIT License - See LICENSE for details.
