Beginner level · Module 2 of 5 · 11 guided hours
How AI Learns from Data
Understand how AI systems learn patterns from examples, how trained models are used and why they make mistakes.
Learning objectives
- Explain features, labels and training data
- Distinguish training a model from using it
- Explain why AI systems make mistakes and how accuracy is measured
Topics
- data as the fuel for AI
- features and labels
- training vs inference
- test data and accuracy
- errors and their causes
- data quality
Lessons
-
Lesson 1 Data, Features and Labels
See how examples with features and labels teach an AI system to recognise patterns.
training datafeatureslabelsdata quality
-
Lesson 2 Training and Using a Model
Distinguish the training phase from the use (inference) phase, and train a simple classifier without code.
modeltraininginferenceconfidence score
-
Lesson 3 Why AI Makes Mistakes
Measure how often AI is right, understand the kinds of errors and why they happen.
test dataaccuracyfalse positives and negativescauses of error
Practical activity
Train a simple image or sound classifier with a no-code tool, test it on new examples and find the situations where it fails.
Expected outcomes
- A concrete understanding of training and testing
- Realistic expectations about AI errors
Assessment
Practical demonstration of the trained classifier with a written explanation of its failures.
Taught live by an instructor — online or in person. Free course lessons are for self-study and do not lead to a certificate — see registration options.