A4.1 Machine learning fundamentals: notes and practice

What you need to know

Our summary of the topic in our own words, not the IB guide.

• Explain what machine learning is and how it differs from a conventionally programmed solution
• Distinguish supervised, unsupervised and reinforcement learning
• Distinguish classification from regression as supervised tasks
• Explain what transfer learning is and why a pre-trained model is reused
• Match real applications such as image classification, natural language processing, sentiment analysis, recommendation and medical diagnosis to the right type of learning
• Define training data, features, labels, a model and inference
• Explain why training and inference have different hardware demands
• Compare CPU, GPU, TPU and specialised accelerators for machine learning work
• Compare running a model on an edge device with running it in a data centre or cloud platform
• Recommend a hardware deployment for a described machine learning scenario and justify it

Practice questions

Original questions written for the 2027 course, marked as you go. Easiest first.

• Supervised, unsupervised and reinforcement learningWritten · Core
• Machine learning or fixed rules for lunchesWritten · Core
• Classification or regression for rainfallWritten · Core
• Bike-share demand model: classification or regressionWritten · Core
• Edge computing for forest camerasWritten · Stretch
• Bike-share model: updating predictions every 5 minutesWritten · Stretch

Exam tips for A4.1

• Be ready to define training data, features, labels, model and inference in one line each.
• Classification predicts a category and regression predicts a number. Name which one a scenario needs.
• When recommending hardware, consider where the model runs, how fast it must answer and what it costs.