logo

Unit 10: Review

Learning outcomes

By the end of this unit you should:

  • know the 38 key terms related to expert systems
  • have practised explaining the theory and application of expert systems
Rubik

Activity 1: Word to Definition

Work alone or in pairs. State a concise definition for each word, then check the answer.

A computer program that uses artificial intelligence (AI) technologies to simulate the judgement and behavior of a human or an organization with expert knowledge in a particular field.

The collection of facts and rules that an expert system uses to make decisions.

Rules are statements that guide the decision-making process, typically formulated as "if-then" statements.

Pieces of information considered to be true, used as the basis for reasoning or decision-making in expert systems.

The part of an expert system that applies rules to facts (or other rules) in the knowledge base in order to infer new facts or make decisions.

A method of reasoning in expert systems where the inference engine begins with known facts and uses the rules to infer new facts.

A method of reasoning in expert systems where the inference engine starts with goals and works backwards to find facts that support those goals.

A part of an expert system that allows it to explain its reasoning and how it arrived at a particular conclusion.

Knowledge that has been documented and can be shared.

Personal knowledge based on individual experiences, not easily shared or documented.

Knowledge that isn't written down or stated, but is implied or embedded in other knowledge.

The process of obtaining, creating, or building knowledge for use in an expert system.

How knowledge is stored and organised within a system, making it retrievable and usable by an inference engine.

The process an expert system uses to deduce new information from the facts and rules in its knowledge base.

The process of ensuring that the knowledge in the expert system is accurate, consistent, and reliable.

The process of improving the knowledge base by eliminating errors or redundancies, and by adding new knowledge.

type of AI that allows a system to learn and improve from experience without being explicitly programmed.

A system that uses rules as its knowledge base, applying them to facts to infer conclusions.

Systems that use a set of production rules (if-then excecute this action rules) to represent knowledge.

Structures for representing stereotypical situations. They are clusters of knowledge that contain attributes (slots) and values.

In frames, slots are attributes or properties that define the frame.

The information or data that is assigned to a slot in a frame.

A formal logic system where predicates can be applied to arguments. It allows the formulation of quantified statements that can be analyzed for their truth or falsehood.

A logical system that handles concepts with degrees of truth, rather than absolute true or false, useful when dealing with imprecise or vague information.

A graphical representation of knowledge where nodes represent concepts and edges represent relationships between concepts.

A system of logic based on the semantic relations of natural language and the concepts which are inherent in a knowledge base.

A type of probabilistic graphical model that uses Bayesian inference for probability computations. Bayesian networks are used to model uncertainty in complex domains.

A finite directed graph with no directed cycles. It consists of vertices and edges, with each edge directed from one vertex to another.

In the context of a graph, a source is a node that has no incoming edges.

In the context of a graph, a sink is a node that has no outgoing edges.

A flowchart-like structure in which each internal node represents a decision, each branch represents an outcome of that decision, and each leaf node represents a class label (an outcome).

A type of diagram that represents an algorithm or process, showing the steps as boxes of various kinds, and their order by connecting them with arrows.

A table that represents a set of rules, with each rule being a row that includes a condition and an action.

A network of rules where each rule is a node, and the links between nodes represent the relationship between rules.

A graphical representation of rules and their relationships, similar to a rule network.

A diagram that depicts the behavior of a system by showing its states and the transitions between those states.

Tools and techniques for visually representing and analyzing data produced by natural language processing (NLP) systems.

Diagrams that show the classes of a system, their interrelationships, and the operations and attributes of each class, used in the Unified Modeling Language (UML).

Activity 2: Vocabulary translation

Hover over a word to reveal the Japanese translation.

Work alone, in pairs or groups. State the Japanese term and see if you partner can state the English translation.

  1. expert system (translation)
  2. knowledge base (translation)
  3. rules (translation)
  4. facts (translation)
  5. inference engine (translation)
  6. forward chaining (translation)
  7. backward chaining (translation)
  8. explanation facility (translation)

  9. explicit knowledge (translation)
  10. tacit knowledge (translation)
  11. implicit knowledge (translation)
  12. knowledge acquisition (translation)
  13. knowledge representation (translation)
  14. knowledge inferencing (translation)
  15. knowledge validation (translation)
  16. knowledge refinement (translation)
  17. machine learning (translation)
  18. rule-based systems (translation)
  19. production systems (translation)
  20. frames (translation)
  21. slots (translation)
  22. values (facets) (translation)
  23. first order logic (translation)
  24. fuzzy logic (translation)
  25. semantic networks (translation)
  26. conceptual graphs (translation)
  27. Bayesian networks (translation)
  28. directed acyclic graph (translation)
  29. source (translation)
  30. sink (translation)

  31. decision tree (translation)
  32. flowchart (translation)
  33. rule table (translation)
  34. rule network (translation)
  35. rule graph (translation)
  36. state transition diagram (translation)
  37. natural language processing visualization (translation)
  38. UML class diagrams (translation)

Master list

Activity 3: Vocabulary

This list contains of the important technical terms related to expert systems. The terms are grouped by the unit in which they were introduced.

Work alone, in pairs or groups. Describe, explain and provide examples for each of these terms.

  1. expert system
  2. knowledge base
  3. rules
  4. facts
  5. inference engine
  6. forward chaining
  7. backward chaining
  8. explanation facility

  9. explicit knowledge
  10. tacit knowledge
  11. implicit knowledge
  12. knowledge acquisition
  13. knowledge representation
  14. knowledge inferencing
  15. knowledge validation
  16. knowledge refinement
  17. machine learning
  18. rule-based systems
  19. production systems
  20. frames
  21. slots
  22. values (facets)
  23. first order logic
  24. fuzzy logic
  25. semantic networks
  26. conceptual graphs
  27. Bayesian networks
  28. directed acyclic graph
  29. source
  30. sink

  31. decision tree
  32. flowchart
  33. rule table
  34. rule network
  35. rule graph
  36. state transition diagram
  37. natural language processing visualization
  38. UML class diagrams

Review

Can you:

  1. do this
  2. do that
  3. and do this

Running count: 38 of 38 concepts covered.