Computer Science › Section L · Artificial intelligence › Topic L.4
Additional areas: knowledge and learning
Perceiving and searching are not enough: an intelligent agent needs a store of knowledge it can use and keep up to date, and the ability to learn what nobody programmed into it. This topic covers how knowledge is represented, why using it is tricky, the main kinds of machine learning, and evolution-inspired genetic algorithms.
In this topic
- The knowledge problem
- Ways to represent knowledge
- Worked example: inheritance in a semantic net
- Finding what is relevant
- The frame problem
- Ways machines learn
- Supervised learning in practice
- Worked example: a nearest-neighbour classifier
- Discovery
- Worked example: one generation of a genetic algorithm
- Common mistakes to avoid
- Key takeaways
This topic is part of Wuanberri Pro. Checking your access…