knowledge base
In plain wordsA store of facts and rules that a program can reason with: like a database, but organized so that new conclusions can be worked out from it, not just looked up.
- 1
Symbolic AI
A collection of knowledge expressed in a formal knowledge representationknowledge representation, n.: The study of how to record knowledge about objects, categories, rules and events in a precise format, so that a program can reason with it and reach conclusions nobody typed in. language — facts, rules, ontologicalontology, n.: A carefully defined vocabulary for a subject such as medicine, spelling out each kind of thing, how kinds nest inside one another, and which connections between them are allowed. axioms or framesframe, n.: In classic AI, a ready-made template for a familiar kind of thing or event, such as a kitchen or a job interview, with blanks to fill in and sensible default values. — over which an inference engineinference engine, n.: The part of an AI system that does the working-out: in older AI, the program that applies rules to facts; in today's AI, the software that runs a trained model to produce answers. can derive new facts. Unlike a conventional database, which returns what was stored, a knowledge base supports entailment: asking whether a statement follows from its contents, including statements never explicitly entered. In an expert systemexpert system, n.: A program that stores a human specialist's know-how as many if–then rules and uses them to give advice or make decisions in a narrow field, such as diagnosing infections or configuring computers., the knowledge base holds the domain expertise and is kept separate from a general-purpose inference engine so that each can be changed independently. Large examples include CycCyc, prop. n.: An AI system built by specialists who spent decades typing in millions of everyday truths, such as 'people cannot be in two places at once', hoping to give computers common sense., WikidataWikidata, prop. n.: A free, shared collection of facts about millions of things — people, places, books, chemicals — kept by volunteers in the Wikipedia family and laid out so programs can use it as easily as people. and other knowledge graphsknowledge graph, n.: A huge web of facts stored as connections between things — 'Paris is the capital of France', 'Marie Curie won a Nobel Prize' — that computers can search, combine and reason over..
The knowledge base contains 4,000 rules about pump failures and their symptoms.
- 2
AI engineering
Informally, any curated collection of documents that a chatbot or AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. searches to answer questions, such as the help-center articles behind a retrieval-augmented generationretrieval-augmented generation, n.: Giving an AI an open-book exam: before answering, it looks up relevant passages in a set of documents and bases its reply on them, often citing where each point came from. system. No formal reasoning is implied; the term here means a reference library rather than a logical theory.
Origin
The term spread in the 1970s with knowledge-based systems such as DENDRALDENDRAL, prop. n.: A program begun at Stanford in 1965 that worked out the structure of chemical molecules from laboratory measurements using rules taken from expert chemists. It is usually called the first expert system. and MYCINMYCIN, prop. n.: A 1970s Stanford program that advised doctors on blood infections and antibiotics by applying hundreds of if–then rules from specialists. It performed about as well as experts but was never used on patients., as Edward Feigenbaum and colleagues at Stanford argued that an expert system's competence comes mainly from its domain knowledge rather than from its inference method.
Related
- knowledge representationknowledge representation, n.: The study of how to record knowledge about objects, categories, rules and events in a precise format, so that a program can reason with it and reach conclusions nobody typed in.
- inference engineinference engine, n.: The part of an AI system that does the working-out: in older AI, the program that applies rules to facts; in today's AI, the software that runs a trained model to produce answers.
- expert systemexpert system, n.: A program that stores a human specialist's know-how as many if–then rules and uses them to give advice or make decisions in a narrow field, such as diagnosing infections or configuring computers.
- knowledge graphknowledge graph, n.: A huge web of facts stored as connections between things — 'Paris is the capital of France', 'Marie Curie won a Nobel Prize' — that computers can search, combine and reason over.
- ontologyontology, n.: A carefully defined vocabulary for a subject such as medicine, spelling out each kind of thing, how kinds nest inside one another, and which connections between them are allowed.
- knowledge engineeringknowledge engineering, n.: The craft of collecting what human experts know — through interviews, observation and documents — and turning it into rules or structured data that a computer system can use.
Mentioned in
CycCyc, prop. n.: An AI system built by specialists who spent decades typing in millions of everyday truths, such as 'people cannot be in two places at once', hoping to give computers common sense., Edward FeigenbaumEdward Feigenbaum, prop. n.: An American computer scientist who pioneered expert systems, programs that capture specialists' knowledge as rules to solve problems in fields such as chemistry and medicine., expert systemexpert system, n.: A program that stores a human specialist's know-how as many if–then rules and uses them to give advice or make decisions in a narrow field, such as diagnosing infections or configuring computers., inferenceinference, n.: Drawing a conclusion from evidence. In today's AI it most often means running an already-trained model to get an answer, as opposed to training it., inference engineinference engine, n.: The part of an AI system that does the working-out: in older AI, the program that applies rules to facts; in today's AI, the software that runs a trained model to produce answers., knowledge graphknowledge graph, n.: A huge web of facts stored as connections between things — 'Paris is the capital of France', 'Marie Curie won a Nobel Prize' — that computers can search, combine and reason over., knowledge representationknowledge representation, n.: The study of how to record knowledge about objects, categories, rules and events in a precise format, so that a program can reason with it and reach conclusions nobody typed in., MYCINMYCIN, prop. n.: A 1970s Stanford program that advised doctors on blood infections and antibiotics by applying hundreds of if–then rules from specialists. It performed about as well as experts but was never used on patients., rule-based systemrule-based system, n.: A computer system that makes decisions by following a list of 'if… then…' rules written by people, rather than by learning from examples., WikidataWikidata, prop. n.: A free, shared collection of facts about millions of things — people, places, books, chemicals — kept by volunteers in the Wikipedia family and laid out so programs can use it as easily as people., closed-world assumptionclosed-world assumption, n.: The rule of treating whatever a system cannot confirm as false: if a library's catalog does not list a book, the library is assumed not to have it., DENDRALDENDRAL, prop. n.: A program begun at Stanford in 1965 that worked out the structure of chemical molecules from laboratory measurements using rules taken from expert chemists. It is usually called the first expert system., Douglas LenatDouglas Lenat, prop. n.: An American computer scientist who spent four decades building Cyc, a giant hand-written database of everyday common sense meant to let computers reason like people., knowledge acquisition bottleneckknowledge acquisition bottleneck, n.: The problem that getting knowledge out of human experts and into a computer by hand is so slow and costly that it limited how far classic expert systems could go., knowledge engineeringknowledge engineering, n.: The craft of collecting what human experts know — through interviews, observation and documents — and turning it into rules or structured data that a computer system can use., Tom MitchellTom Mitchell, prop. n.: An American computer scientist who wrote a classic machine-learning textbook with the field's most quoted definition of learning, and founded the first university department devoted to machine learning.