What do you want to learn today?
Search practical, beginner-friendly tutorials across Machine Learning, Deep Learning, Generative AI, LLMs, RAG, Agentic AI and production AI engineering. With worked equations, small reproducible numbers, and complete Python implementations.
Modern AI Learning Roadmap
Step-by-step conceptual progression from zero to production
Machine Learning
Foundations, Regression, Trees, Evaluation
Deep Learning
Backprop, CNNs, Transformers
Generative AI
Diffusion, VAEs, Multimodal Models
LLMs & RAG
Vector Search, Context, Chunking
Agentic AI
Tool Calling, Memory, MCP, Multi-Agent
AI Engineering & MLOps
FastAPI, Docker, CI/CD, Drift Monitoring
Goal-based learning
Choose your learning path
One complete AI library, four focused ways to learn. Start with foundational concepts, jump directly into a specialized subject, develop advanced production expertise, or build working software.
Start from the beginning
New to machine learning? Follow a sensible progression from core intuition to working algorithms, data preprocessing, and evaluation.
Recommended sequence:
Learn a specific topic
Already familiar with basic concepts? Jump straight into modern AI subjects without being forced to start at the beginning.
Direct entry points:
- Deep LearningIntro
- Generative AIIntro
- Large Language ModelsIntro
- Agentic AIIntro
Deepen professional expertise
For engineers and ML practitioners seeking advanced architectures, evaluation benchmarks, reliability, and system design.
Build practical AI systems
Turn theory into working software with 12 complete project handbooks built from scratch with code, tests, and Streamlit UIs.
Production-Grade Software
12 Real Machine Learning & AI Projects
Full-fidelity handbooks with reproducible data pipelines, baseline comparisons, unit tests, Streamlit interfaces, and downloadable starter ZIPs. No mock data or half-finished code.
Chat With Your PDFs - Build Your Own RAG Assistant
Ask questions about real PDFs, retrieve supporting passages and verify page-level citations using a runnable, offline-first RAG system.
Deliverable Outcome
A Streamlit PDF question-answering app with page-aware extraction, overlapping chunks, TF-IDF vector retrieval, citations, local index persistence, tests and optional OpenAI summaries.
# projects/pdf-rag/tests/test_rag.py
# 10 automated unit tests in suite:
• test_page_numbers_and_source_ids()
• test_overlap_preserves_boundary_and_pages()
• test_retrieval_and_citations_have_original_page()
• test_embedded_prompt_injection_is_only_pdf_evidence()
• test_saved_index_roundtrip_and_tampering_detected()
# (+5 more in suite: corrupt-PDF, abstain, dedup, citations, real-overlap)
📦 local-pdf-rag-assistant.zip (Complete starter scaffold)
🧪 10 unit tests included (historical CI run: 10 passed)Titanic Survival Predictor
A classic hands-on classification project rebuilt as a complete beginner-friendly handbook from raw CSV to a working prediction app.
House Price Predictor
Build a real-estate-style price estimator and compare linear, regularized and ensemble regression models.
Credit Card Fraud Detector
Learn how real fraud problems differ from ordinary classification because fraudulent transactions are rare.
Customer Segmentation
Turn 541,909 real retail transactions into customer groups and learn why clustering can reveal patterns without labels.
Retail Sales Forecaster
Build a forecasting workflow that learns trend and seasonality from historical store sales.
Movie Recommendation System
Build a movie-similarity recommender from a reusable CC0 ratings dataset, then compare popularity, content, collaborative and hybrid ranking strategies.
Disaster Tweet Detector
Move from classic text features to modern Transformers while solving a recognizable NLP classification problem.
Handwritten Digit Recognizer
Train a neural network and CNN on handwritten digits, then turn the model into a small image prediction app.
AI Content Creator
Create, rewrite, summarize and review real business copy with a working Streamlit studio, optional LLM API generation and strict structured output checks.
PDF RAG Assistant
Ask questions about real PDFs, retrieve supporting passages and verify page-level citations using a runnable, offline-first RAG system.
AI Research Assistant
Build an auditable research tool that plans a question, reads real source text, checks original quotes and publishes a clearly cited evidence brief.
Model to Production
Turn a trained churn model into a real FastAPI service with strict validation, versioned artifacts, Docker, CI, drift checks and rollback.
Looking for foundational tutorials that teach the concepts step by step before building?
Curriculum Map
Browse by topic
Structured into 6 specialized tracks covering 17 modules and 167 verified lessons.
Machine Learning
Foundations, data preparation, classical algorithms, evaluation and forecasting.
Key topics:
- • Linear Regression
- • Random Forests
- • PCA
- • Gradient Descent
Deep Learning
Neural networks, backpropagation, CNNs, transformers, vision and advanced models.
Key topics:
- • Backpropagation
- • Convolutional Nets
- • Attention
- • Transformers
Generative AI
VAEs, GANs, diffusion, multimodal generation, evaluation and deployment.
Key topics:
- • Latent Diffusion
- • Score Matching
- • VAEs & GANs
- • Multimodal
LLMs & RAG
Tokenization, transformers, embeddings, vector databases, RAG and LLMOps.
Key topics:
- • Vector Embeddings
- • Hybrid Retrieval
- • Reranking
- • Context Windows
Agentic AI
Tool calling, memory, planning, MCP, multi-agent systems, safety and deployment.
Key topics:
- • Tool Calling
- • Agent Memory
- • ReAct Planning
- • Multi-Agent MCP
AI Engineering
Production pipelines, serving, monitoring, reliability, CI/CD and system design.
Key topics:
- • FastAPI Serving
- • Docker Containers
- • Drift Detection
- • CI/CD Pipelines
High-Impact Starting Points
Recommended for you
Hand-picked cornerstone lessons featuring interactive diagrams, worked calculations, and clear intuition.
Linear Regression Step by Step
Build intuition for the line of best fit, loss and a complete Python workflow.
Neural Networks Explained
Understand neurons, layers, activations and how a network learns from data.
Retrieval-Augmented Generation (RAG)
Learn retrieval, grounding, embeddings and the complete RAG information flow.
What Is an AI Agent?
Connect tools, planning, memory and decisions into an agentic workflow.
Career preparation
Preparing for an interview?
Practice ML, Python, SQL, LLM/RAG and system-design questions with dedicated interview lessons.
10 Free Interview Handbooks
Download detailed PDFs for Machine Learning, Deep Learning, Generative AI, LLM & RAG, Agentic AI, Python, SQL, System Design, MLOps and Behavioral interviews.
From the blog
Practical ML & AI articles
Deeper guides, comparisons and career articles that complement the lesson curriculum.
Agentic AI Interview Preparation Guide
Prepare for Agentic AI interviews with a structured plan covering tool calling, planning, memory, MCP, multi-agent systems, safety, evaluation, and deployment.
LLM & RAG Interview Preparation Guide
Prepare for LLM and RAG interviews with a step-by-step plan covering Transformers, embeddings, retrieval, reranking, evaluation, safety, and production LLM systems.
Generative AI Interview Preparation Guide
Prepare for Generative AI interviews across generative modelling, VAEs, GANs, diffusion, multimodal AI, fine-tuning, evaluation, safety, and deployment.
Ready to master machine learning and artificial intelligence?
Start with zero prerequisites. 167 verified tutorials, 12 full-stack projects, and 10 interview handbooks—free forever.