AI & Machine Learning
A practical path through AI foundations, machine learning, data preparation, neural networks, transformers and LLMs, prompt design, embeddings and RAG, tool-using agents, evaluation, safety, and production operations. Start with the roadmap, then follow the lessons in order or jump to the skills your project needs.
15 lessons · about 0.7 hours
Start the first lesson →
- 01What to Learn in AI, and in What Order A practical map from programming and data basics through machine learning, deep learning, LLM applications, evaluation, and production.
- 02Machine Learning Fundamentals Learn how models use examples to make predictions, and how supervised, unsupervised, and reinforcement learning differ.
- 03Data Preparation and Model Training Turn raw data into trustworthy examples, prevent leakage, and build repeatable training experiments.
- 04Neural Networks and Deep Learning Understand layers, activations, loss, gradient descent, embeddings, and when deep learning is a good fit.
- 05Transformers and Large Language Models Learn tokens, next-token prediction, attention, pretraining, fine-tuning, context windows, and the limits of language models.
- 06Prompting and Structured Outputs Write clear instructions, provide context and examples, constrain responses, and validate model output in code.
- 07Embeddings, Semantic Search, and RAG Use vector representations to retrieve relevant source material and ground language-model answers in your documents.
- 08AI Agents and Tool Use Understand tool-calling loops, bounded autonomy, state, approvals, and when a simple workflow is better than an agent.
- 09AI Evaluation, Safety, and Security Build representative tests, measure retrieval and model quality, defend against prompt injection, and handle sensitive data responsibly.
- 10Putting AI Systems into Production Design dependable model integrations with fallbacks, observability, versioning, cost controls, and human review.
- 11What Is Artificial Intelligence? A Developer's Guide Understand AI, machine learning, deep learning, and generative AI through everyday examples and concrete software decisions.
- 12Python and Math Foundations with Runnable Examples Practice features, vectors, normalization, similarity, probability, and evaluation with Python's standard library.
- 13Train Your First Model from Scratch Run a complete linear-regression experiment, compare a baseline, inspect loss, and evaluate on unseen examples.
- 14AI Specialties and Real-World Examples Explore vision, language, speech, recommendations, anomaly detection, forecasting, reinforcement learning, and generative systems.
- 15Developer Learning Plan and Document-Assistant Capstone Follow a practical study plan with deliverables, build a local retrieval baseline, and grow it into an evaluated AI application.