Patterns and categories
Be able to sort objects into groups based on properties, explain the rule governing the group, and identify when something does not fit.
Everyday explanation
When you sort email messages into folders, you sort by a property: the subject, the sender, or the priority. You could have sorted by date instead. Same messages — different rule.
Finding patterns and dividing things into categories is the foundation of how computers "learn". The system looks at properties and groups information.
Intuition
A category needs a clear rule: "All invoices from supplier A" or "All messages with the word 'urgent'". With the same rule, the same objects always end up in the same group.
Sometimes something does not quite fit — an email might be from a supplier but concern a private matter. Then the rule is too simple. Improving the rule is the core of machine learning, except the computer does it with thousands of examples.
Mastery means
- Sorts objects according to a specified property
- Formulates the rule behind a given sorting
Sign in to do the exercises and build your mastery up.
Sources
Leads to
Part of the goals (41)
- Discoverer — build a game and train a machine
- Statistics for experiments
- Data: collect, clean, document
- Explorer — discover that computers can learn from examples
- Computers that see and hear
- The developer's toolbox
- The mathematics behind the models
- Build an NLP system end to end
- Classical machine learning in practice
- AI for beginners
- Build an AI service that survives production
- Fine-tune and run your own models
- AI, ethics and society
- From blocks to Python
- Train an agent with reward
- Builder — collect data, train a model and test AI critically
- Training neural networks for real
- Fine-tune a model with LoRA
- Build a RAG system you can trust
- AI in production
- Generative models in depth
- Classical ML for real
- Frontier Lab — an independent research project
- Evals in practice
- Language models in practice
- Understand how generative AI works
- An AI service in operation
- Build a memory system for an agent
- Build an agent you can trust
- AI safety in practice
- Responsible AI in practice
- Interpreting a language model
- Reproduce a paper
- Build a voice interface
- Train your first neural network
- Deep reinforcement learning
- Seeing and hearing with AI
- Image classification with convolutional networks
- Run models more cheaply: quantisation
- Multimodal systems
- Build a transformer from scratch