Courses

Free AI courses

Each course follows a full-length video, lesson by lesson, with code you can run and a quiz after every part.

  • Clips at the exact minuteEach lesson plays the part of the video that explains it.
  • Code you can runEvery example ran for real; what you see is what it printed.
  • Diagrams of the ideaDrawn from the board's own examples, so the numbers match.
  • A quiz after every partFive questions, each with the reason for its answer.
The courses

Pick a course

Each course is split into parts, with a quiz at the end of every part.

Generative AI and Agentic AI

Beginner to intermediate · 48 lessons · 8 parts

Build with generative AI and agents from the first LLM call to RAG, tool-using agents, self-correcting loops, harnesses and fine-tuning, the way the videos build them.

Syllabus

  1. 01Generative AI foundations
  2. 02Building with LLMs
  3. 03RAG
  4. 04AI agents
  5. 05Loop engineering
  6. 06Harness engineering
  7. 07Quantization and fine-tuning
  8. 08Production
Start Generative AI and Agentic AI

Follows the End to End Multimodal LLMOps Project video.

LLMOps

Intermediate · 50 lessons · 9 parts

Take an LLM app from a notebook to production: the LLMOps lifecycle, a project you can operate, experiment tracking, evaluation, observability, deployment and the cost and drift you watch after.

Syllabus

  1. 01What LLMOps is
  2. 02Planning and the pipeline
  3. 03Data and model selection
  4. 04Structuring an LLM app for production
  5. 05Tracking and evaluation
  6. 06Monitoring and observability
  7. 07Deployment
  8. 08The end-to-end project
  9. 09The project: a compliance auditor
Start LLMOps

MLOps

Intermediate · 50 lessons · 9 parts

Take a trained model out of the notebook and operate it: a project structure that scales, tracked experiments, versioned data, a served API in a container, CI/CD, and the drift you watch after it ships.

Syllabus

  1. 01What MLOps is
  2. 02Setting up the project
  3. 03The project architecture
  4. 04The running example end to end
  5. 05Experiment tracking with MLflow
  6. 06Versioning data and pipelines with DVC
  7. 07Serving the model
  8. 08Automating with CI/CD
  9. 09Running it after it ships
Start MLOps

AI Security

Intermediate · 52 lessons · 10 parts

Guardrails, LLM evaluation, agent memory and AgentOps: the four things an AI agent needs before it meets real users, each run for real.

Syllabus

  1. 01Getting started
  2. 02LLM security and guardrails
  3. 03NeMo Guardrails
  4. 04LLM evaluation
  5. 05RAG evaluation metrics
  6. 06Short-term agent memory
  7. 07Long-term agent memory
  8. 08Managing agent memory
  9. 09AgentOps: the production stack
  10. 10Deploying and scaling
Start AI Security

Follows the Deep Learning In-depth Tutorials in 5 Hours video.

Deep Learning

Beginner · 41 lessons · 10 parts

Neural networks from the perceptron to CNNs, worked out on the board's own numbers, then built in Keras.

Syllabus

  1. 01What deep learning is
  2. 02The perceptron and the neuron
  3. 03Backpropagation
  4. 04Activation functions
  5. 05Loss functions
  6. 06Optimizers
  7. 07Training deeper networks
  8. 08An ANN in Keras
  9. 09Convolutional neural networks
  10. 10Putting it together
Start Deep Learning

Follows the Complete NLP Machine Learning in One Shot video.

Natural Language Processing

Beginner to intermediate · 52 lessons · 11 parts

NLP from tokenization to transformers: text preprocessing, BoW, TF-IDF and Word2Vec, RNNs and LSTMs, then every block of the transformer, worked out on the board's own examples.

Syllabus

  1. 01Getting started
  2. 02Text preprocessing
  3. 03Turning text into vectors
  4. 04Word embeddings
  5. 05NLP projects with machine learning
  6. 06Recurrent neural networks
  7. 07LSTM, GRU and their practicals
  8. 08Sequence to sequence and attention
  9. 09Transformer building blocks
  10. 10Transformer encoder and decoder
  11. 11From transformers to today's models
Start Natural Language Processing

Follows the Complete Machine Learning in 6 Hours video.

Machine Learning

Beginner · 52 lessons · 10 parts

Every classical machine learning algorithm, from the board intuition and worked numbers to working scikit-learn code.

Syllabus

  1. 01What machine learning is
  2. 02Linear regression
  3. 03Overfitting and regularization
  4. 04Logistic regression and metrics
  5. 05Naive Bayes and KNN
  6. 06Decision trees
  7. 07Ensemble methods
  8. 08Support vector machines
  9. 09Unsupervised learning
  10. 10Putting it together
Start Machine Learning

Follows the Complete Statistics for Data Science in 6 Hours video.

Statistics

Beginner · 57 lessons · 10 parts

Statistics for data science from the first idea to hypothesis tests, worked out on the board's own numbers, then computed in Python.

Syllabus

  1. 01What statistics is
  2. 02Describing data with tables and charts
  3. 03Centre and spread
  4. 04Percentiles, quartiles and box plots
  5. 05The normal distribution
  6. 06Probability
  7. 07Probability distributions
  8. 08Estimation and hypothesis testing
  9. 09Statistical tests
  10. 10Relationships between variables
Start Statistics

Follows the EDA and Feature Engineering video.

EDA and Feature Engineering

Beginner to Intermediate · 72 lessons · 12 parts

Look at a dataset until you understand it, then turn it into features a model can learn from, without leaking and without silently doing nothing.

Syllabus

  1. 01The process, and the traps
  2. 02Reading and auditing a dataset
  3. 03Charts that answer a question
  4. 04Missing values
  5. 05Outliers
  6. 06Categorical features
  7. 07Scaling and transformation
  8. 08Features from dates, times and durations
  9. 09Imbalanced data
  10. 10Feature selection
  11. 11Doing it without leaking
  12. 12Project: a house price pipeline
Start EDA and Feature Engineering

Python for AI

Beginner · 43 lessons · 9 parts

Python from your first line to classes, Pydantic, async and tests, taught on one AI program.

Syllabus

  1. 01First lines of Python
  2. 02Many values
  3. 03Functions
  4. 04Files, JSON and errors
  5. 05Classes and objects
  6. 06Advanced Python
  7. 07Types and validation
  8. 08Waiting on models
  9. 09A real project
Start Python for AI

Git and GitHub

Beginner · 26 lessons · 6 parts

Track your work, undo mistakes, branch an experiment and put a project on GitHub the way a team expects to find it.

Syllabus

  1. 01Starting out
  2. 02History
  3. 03Branches
  4. 04GitHub
  5. 05Undoing things
  6. 06A repository a team can read
Start Git and GitHub
Vidya · AI tutor

An AI tutor on every lesson

Start a call and Vidya teaches the lesson on your screen by voice, asking you questions as she goes.

  • Teaches by voice. The lesson on your screen, one small piece at a time.
  • Marks as she talks. The heading, the line of code, the clip she means.
  • Asks you questions. About the line or idea she just explained.