Machine learning
Systems that learn patterns from data instead of following hand-written rules.
A machine learning model is trained on examples to make predictions or decisions on new data. Its behaviour depends on its training data, its algorithm and its settings, so it can change when retrained, unlike traditional code.
On the exam
Because model behaviour comes from data, auditors look at data quality, training and validation, not only at code reviews.
Related terms
- Supervised, unsupervised and reinforcement learningThree main ways models learn.
- Deep learning and neural networksModels built from many layers of connected nodes that learn complex patterns.
- Training, validation and test dataSeparate datasets to build, tune and fairly measure a model.
AAIA Test yourself on this with timed AAIA practice questions in the AAIA Exam Simulation Hub, or read the free AAIA exam guide.
Test yourself with today’s question of the day.
