Declarative knowledge

  • Refers to facts and info that describe the world, answering the what type of knowledge.
  • Example: Knowing “Paris it the capital of France”
  • This knowledge is often stored in databases or knowledge bases and expressed in logical statements, forming the foundation for more complex reasoning and problem-solving in AI systems.

Procedural knowledge

  • The knowledge of how to perform tasks and procedural processes, answering the how type of questions.
  • Example: Steps to solve a mathematical problem or the procedure to start a car.
  • This knowledge is embedded in algorithms or control structures, enabling AI systems to execute tasks, perform actions and solve problems step-by-step.

Meta knowledge (knowledge about knowledge)

  • It is understanding which types of knowledge to apply where
  • Example: Knowing which algorithm to use to solve the problem at hand
  • Crucial for systems that need to adapt or optimize their performance, meta-knowledge helps in selecting the most appropriate strategy or knowledge base for a given problem.

Heuristic knowledge

  • It includes rules of thumb, educated guesses, and intuitive judgements derived from experience
  • Example: using an educated guess to approximate a solution when time is limited.
  • Often used in problem solving and decision making processes where exact solutions are not feasible, helping AI systems to arrive at good enough solutions quickly

Structural knowledge

  • It refers to the understanding of how different pieces of knowledge are organized and related to each other
  • Example: Understanding the hierarchy of concepts a taxonomy or the relationships between different entities in a semantic network
  • This knowledge is essential for organizing information within AI systems, allowing for efficient retrieval, reasoning and inferencing based on the relationships and structures defined.