Topic A4 is a Higher Level (HL) topic only, so everything here is examined at HL. This unit covers what machine learning actually is and the main types the course expects you to know: supervised, unsupervised and reinforcement learning, plus deep learning and transfer learning. It finishes with the hardware that machine learning runs on.
Slide 1 / 4
What machine learning is
Machine learning is a subfield of artificial intelligence: algorithms and statistical models that let computers perform tasks without being explicitly programmed with fixed rules for every case.
Instead of following a fixed set of instructions, an ML algorithm learns patterns from data, adjusts its output based on past outcomes, and improves its accuracy over time.
It is commonly used to make predictions, to classify and categorize data, and to identify patterns in data.
The more good-quality examples the model is fed, the better it usually performs, just like a robot that improves each time it plays a game.
Check you've got it
0/4
1. Which statement best describes machine learning as the course defines it?
2. In supervised learning, what is the difference between classification and regression?
3. Which type of machine learning best fits an agent that takes actions in an environment to maximize cumulative reward?
4. According to the book, what does the word deep in deep learning refer to?
Free revision content. Multiple-choice answers are marked instantly. Written answers are marked by AI on /free-mark.