Concepts / Symbolic AI

Symbolic AI

Artificial intelligence is the effort to automate intellectual tasks normally performed by humans.

  • Programming

From Human Work to AI

When people ask whether a computer is intelligent, a useful starting point is to ask what kind of human intellectual work the computer is designed to perform. Artificial intelligence is the effort to automate intellectual tasks normally performed by humans. This definition describes a goal, not one single technique. AI is therefore a broad field that includes machine learning, deep learning, and approaches that do not involve learning.

includesincludesincludesincludesArtificialintelligenceAutomating humanintellectual tasksSymbolic AIExplicit rulesMachine learningAn approach within AIDeep learningAn approach within AINon-learningapproachesApproaches that do notinvolve learning
What contains what, and where do symbolic AI and machine learning fit within artificial intelligence?

Following Explicit Rules

Symbolic AI describes knowledge and decisions directly through explicit rules handcrafted by programmers. A rule can connect stated information to a conclusion: if the required conditions are present, produce the specified result. The important feature is that the system's decision logic is written out explicitly rather than obtained through a learning process.

A Rule-Based Classification

Use explicit facts and an if-then rule to determine whether an object belongs to a named category.

Start with facts: The system is given the facts that an object is a robin and that every robin is a bird.

Apply a rule: The programmer has written the rule: if something is a bird, classify it as an animal.

Produce a conclusion: Because the facts identify the object as a bird, the explicit rule produces the conclusion that it is an animal.

The system reaches the conclusion by applying programmer-written rules to explicit facts.

identified asmatches conditionproducesrobinObject identityBird to animalIf bird, then animalanimalConclusionbirdCategory fact
How do explicit facts and if-then rules combine to produce a conclusion?

Two Routes to an Intelligent Result

AspectSymbolic AIMachine learning
How knowledge is suppliedProgrammers describe knowledge and decisions through explicit rulesThe system is built for problems where writing all the rules is extremely difficult
Best fitProblems whose logic can be described clearlyComplex, fuzzy problems
Relationship to AIOne approach within the broader field of AIOne approach within the broader field of AI

Symbolic AI and machine learning are two routes to an intelligent-looking result. In symbolic AI, programmers describe the relevant knowledge and decisions directly. In machine learning, the system is intended for problems where writing all the necessary rules would be extremely difficult. Machine learning is not separate from AI; it is one approach within the broader field.

usesaddressesSymbolic AIProgrammer-written rulesExplicit knowledgeRules described directlyMachine learningApproach fordifficult-to-write rulesComplex fuzzy problemRules extremely difficultto write
What is different about how symbolic AI and machine learning acquire the knowledge used to make decisions?

Clear Logic and Fuzzy Inputs

Explicit rules work well when the logic of a problem can be described clearly. The programmer can state the relevant conditions and the decisions that follow from them. The situation changes when the problem is complex and fuzzy. For image classification, speech recognition, and language translation, working out all the explicit rules needed to describe the solution proved intractable. Machine learning arose as an approach for these kinds of problems.

supportsmotivatedClear logicalproblemConditions can be describedExplicit rulesHandcrafted by programmersComplex fuzzyproblemAll rules are difficult todescribeMachine learningApproach for these problems
How does the problem change when it has clear rule-based conditions versus ambiguous or fuzzy inputs?

Image classification, speech recognition, and language translation illustrate the complex, fuzzy side of the distinction. The source describes these as tasks for which writing all the explicit rules needed to describe the solution proved intractable. This does not mean that symbolic AI has no value; it means that the suitability of an approach depends on the kind of problem being addressed.

Check Your Classification

EASY

A team wants to build a system for a problem whose logic can be described clearly using programmer-written if-then rules. Which approach is the better fit according to the distinction in this article, and why?

Hints
  • Look at how the problem's logic is described.
  • Compare explicit handcrafted rules with the problem types associated with machine learning.

What do you think happens?

Which approach is the better fit for a problem whose logic can be described clearly using programmer-written if-then rules?

  • Symbolic AI
  • Machine learning
  • Neither approach can use explicit logic
Reveal answer

Answer: Symbolic AI

Symbolic AI depends on explicit rules handcrafted by programmers and is suitable for problems whose logic can be described clearly.

  • Treating artificial intelligence and machine learning as synonyms.

    AI is a broad field that includes machine learning and approaches that do not involve learning.

    Fix: Describe machine learning as one approach within the broader field of artificial intelligence.

  • Assuming symbolic AI means that a system learns its rules automatically.

    Symbolic AI depends on explicit rules handcrafted by programmers.

    Fix: Ask who supplied the decision logic: programmers state it directly in symbolic AI.

  • Assuming explicit rules are equally practical for every task.

    The source identifies these as complex, fuzzy problems for which working out all the explicit rules proved intractable.

    Fix: First classify the problem as clearly logical or complex and fuzzy before choosing the approach.

Key Takeaways

  1. Artificial intelligence is the effort to automate intellectual tasks normally performed by humans.
  2. AI is a broad field that includes machine learning, deep learning, and approaches that do not involve learning.
  3. Symbolic AI uses explicit rules handcrafted by programmers.
  4. Explicit rules suit problems whose logic can be described clearly.
  5. Machine learning arose as an approach for complex, fuzzy problems such as image classification, speech recognition, and language translation, where writing all the rules is extremely difficult.

Key Takeaways

  • Artificial intelligence is defined by the human intellectual tasks it aims to automate, not by one particular technique.
  • Symbolic AI represents knowledge and decisions through explicit rules handcrafted by programmers.
  • Machine learning is one approach within AI, especially associated in this distinction with complex, fuzzy problems.
  • The usefulness of explicit rules depends on whether the problem's logic can be described clearly.
  • Image classification, speech recognition, and language translation are examples of problems for which writing all explicit rules proved intractable.