CIE IGCSE | 6.3.2 Characteristics of AI

Lesson objective

Describe AI’s main characteristics: collecting data, rules for using it, reasoning and, in some systems, learning and adaptation.

Learn

6.3.2 | CHARACTERISTICS OF AI

01 | THE CHARACTERISTICS IN THE SPECIFICATION

The specification describes AI through the collection of data and rules for using that data, the ability to reason, and the fact that it can include the ability to learn and adapt.

These ideas describe simulated intelligent behaviour, not a claim that the computer has human thoughts or feelings.

Can include is important: learning is not required in every AI system. An expert system can reason using fixed knowledge and rules.

02 | DATA: WHAT INFORMATION IS AVAILABLE?

Data supplies the information an AI system uses. It can come from user answers, records, sensors, images or other appropriate sources.

Different tasks need different information
SystemPossible data
Printer troubleshooting expert systemUser answers about power, paper and error indicators
Image classifierImages and labels during training; a new image during use
Prediction systemRelevant past observations and new input values

Collecting data is not itself AI. The method used to interpret it and produce a result matters.

Relevant, accurate information is more useful than simply a large amount. Missing, wrong or unrepresentative information can reduce the quality of conclusions.

03 | RULES: HOW WILL THE DATA BE USED?

A rule specifies how information leads to a conclusion or action. In an expert system, rules can be written explicitly using expert knowledge.

Teaching rule: IF the printer has power AND paper is absent THEN recommend checking the paper tray.

The system checks the stated conditions against the available facts. If they match, the corresponding conclusion can follow.

A rule may combine several facts. It is not a random answer and does not require the computer to have personal experience.

04 | REASONING: CONNECT FACTS TO A CONCLUSION

Reasoning means using information and relationships or rules to reach a conclusion.

A recommendation follows from specified evidence and a rule
StepTeaching expert-system example
Available factsPower is present; paper is absent
Relevant ruleIf power is present and paper is absent, recommend checking the tray
CheckBoth stated conditions match
ConclusionRecommend the paper-tray check

The result is conditional on the facts and rule being appropriate. It does not prove that the paper tray is the only possible fault.

The AI characteristic is the simulated reasoning process. Merely storing the answers in a file does not by itself explain that process.

05 | FOLLOW THE INFORMATION PATH

This is a simplified view, not a requirement that all AI algorithms have identical internal steps. The next lesson examines specific expert-system and machine-learning components.

06 | LEARNING: CHANGE USING EXPERIENCE OR DATA

In machine learning, a program can adapt its processes or data using training information. Training changes a model so it can perform a task based on patterns in the data.

Example: labelled material images can be used to train a classifier. The model is adjusted during training to distinguish categories using relevant features.

This is different from a person manually writing a separate rule for every image. People still choose the task, training method, examples and evaluation criteria.

Learning is a computational adaptation process; it does not establish human understanding.

07 | ADAPTATION: WHAT ACTUALLY CHANGES?

Adaptation is a change in the system’s model, processes or data that affects later behaviour.

Changing an answer is not the same as learning
SituationWhat changes?
Training a classifierModel values are adjusted using examples
Updating a rule-based system manuallyA person changes its knowledge or rules
Using a fixed trained classifierInput and output change, but the model may remain unchanged

A different input can produce a different output even when the method is fixed. Do not call every new answer evidence of adaptation.

Automatic learning differs from a programmer editing the system by hand, although both can change behaviour.

08 | TRAINING AND USE ARE DIFFERENT

Training: information is used to adapt the model.

Use, or inference: the trained model processes a new input to produce a result.

A model can be trained first and then deployed without changing during ordinary use. Some systems support further or ongoing learning, but this is not universal.

Performance should be checked using suitable data not used to fit the model. A system that performs well on familiar training examples may still fail on unfamiliar cases.

09 | COMPARE THE TWO COURSE APPROACHES

Both can simulate intelligent behaviour without continuously updating themselves
CharacteristicExpert-system exampleMachine-learning example
DataFacts and user answersTraining examples and new inputs
MethodExplicit knowledge and rulesRelationships represented by an adapted model
Reasoning / inferenceApply rules to reach a conclusionUse the model to produce a prediction or classification
LearningNot required for a fixed rule-based systemTraining adapts the model
Change during ordinary useNot necessarilyNot necessarily

This is the comparison used in this course. Real systems can combine rule-based and learned components.

10 | QUALITY, BIAS AND LIMITS

Wrong input: an expert system can reach an unsuitable conclusion if a user supplies an incorrect fact.

Incomplete rules: a rule-based system may not cover an unusual situation.

Unrepresentative training: a model may work better for familiar cases than poorly represented cases.

Changing conditions: relationships learned from past data may not remain useful for a new environment.

Learning does not guarantee improvement on every task or every group. Testing and careful evaluation remain necessary.

11 | A WORKED COMPARISON

Two systems help sort recyclable items.

System A: applies an explicit rule to known item information, such as “if the recorded material is aluminium, assign the metal category”.

System B: uses a model trained on labelled images to predict the category of a new image.

Both use data and a method to produce a result. System A’s rule can stay fixed; System B’s model was adapted during training. Neither must alter itself every time a new item is processed.

The important distinction is how the method was obtained and whether it changes, not simply whether the output varies.

12 | COMMON MISTAKES

  • Collecting data automatically means AI: explain how it is used.
  • Reasoning proves human thought: the behaviour is simulated computationally.
  • Every AI learns: fixed expert-system rules can be sufficient.
  • A different output proves learning: a fixed method can respond to different inputs.
  • Training and inference are identical: model adaptation differs from using it.
  • More data guarantees better results: relevance and representation matter.
  • Learning removes bias or errors automatically: evaluation is still needed.

MATCH THE AI CHARACTERISTIC

Terminology

Terminology

Data collection

Obtaining information relevant to a system’s task.

Fact

An item of information treated as available evidence in a reasoning task.

Rule

A specified relationship linking conditions to an action or conclusion.

Reasoning

Using information and relationships to reach a conclusion.

Inference

Applying a method to obtain a result from available information.

Learning

Adapting a model, process or data using training information or experience.

Adaptation

A change to processes or data affecting later behaviour.

Training

Using information to fit or adjust a model.

Trained model

A representation adapted through training and used for later results.

Training example

An item used during model adaptation.

Label

A category or target value associated with an example.

Evaluation data

Suitable information used to check performance, separate from fitting where appropriate.

Expert-system rule

An explicit rule used with knowledge to infer a domain-specific conclusion.

Fixed model

A model not changing during the period of use being considered.

Bias

A tendency producing systematically uneven or distorted outcomes.

Generalisation

Applying learned relationships to inputs beyond the examples used to fit the model.

Questions

Questions

CHECK YOUR UNDERSTANDING

Select all correct choices. Each exact set earns one point.

1. Which characteristics are named in the specification?
2. Which describe rule-based reasoning?
3. Which statements about learning are correct?
4. Which distinguish training and inference?
5. A fixed model gives a different result for a different image. Which are correct?
6. Which affect output quality?
7. Which evaluation statements are correct?
8. Which describe adaptation accurately?

EXPLAIN AND COMPARE

Write your answers before revealing each sample.

1. State the main AI characteristics from the specification.

2. Describe how an expert system uses facts and rules.

3. Explain why learning is not required in every AI system.

4. Compare training and inference in machine learning.

5. Explain why a different answer does not necessarily show adaptation.

6. Explain how unrepresentative examples can affect a trained classifier.

7. Evaluate the claim that more training data always improves AI.

APPLY IT | DID IT LEARN?

A fixed rule-based system recommends checking the paper tray for one printer and checking the power connection for another. A student says the changed recommendation proves it learned. Explain why this conclusion is not justified and what evidence of adaptation would be needed.

Reveal suggested answer

Different facts can match different rules even when the rules are unchanged. A changed recommendation alone is not evidence of learning. Evidence would need to show that the system automatically changed its model, processes or data through learning, affecting later behaviour.

Flashcards

Flashcards

Click to flip. Select the ideas you need to revisit.

0 cards selected for revision.

    Selections are kept while this page is open.

    Workbook

    Workbook

    COMING SOON

    The workbook for 6.3.2 Characteristics of AI is coming soon. Complete the matching task and written questions in your exercise book.