• Algorithm — A detailed sequence of action to perform to accomplish task;
  • Analogical Reasoning — Determining the outcome of a problem by use of analogies. A procedure for drawing conclusions about a problem by using past experience;
  • Artificial Intelligence (AI) — The sub-field of computer science that is connected with symbolic reasoning and problem solving;
  • Artificial Neural Networks (ANN) — Computer technology that attempts to build computers that will operate like a human brain. The machine possesses simultaneous memory storage and work with ambiguous information (See Neural Computing).
  • Associative Memory — The ability to recall complete situations from partial information.
  • Back-propagation — The best-known learning algorithm in neural computing. Learning is done by comparing the computed to sample case outputs.
  • Backward Chaining — A search technique used in production (“IF-THEN” rule) systems that begins with the action clause of rule and works “backward” through a chain of rules in an attempt to find a verifiable set of condition clauses.
  • Case-Based Reasoning (CBR) — Methodology in which knowledge and/or inferences are derived from historical cases.
  • Crossover — The combination of parts of two superior solutions in an attempt to produce even better solutions. A technique used in the genetic algorithm.
  • Data — Raw facts that are meaningless by themselves (such as names or numbers).
  • Data Mining — The activity of looking for very specific, detailed, but unknown, information in data bases. As search for valuable, yet difficult to obtain data.
  • Data Warehouse — The physical repository where relational data are specially organized to provide enterprise-wide, cleaned data in standardized format.
  • Data Warehouse — The physical repository where relational data are specially organized to provide enterprise-wide, cleaned data in standardized format.
  • Declarative Rules — Rules that state all the facts and relationships related to a problem.
  • Deductive Reasoning — In logic, reasoning from the general to the specific. Conclusions (inferences) follow premises. Consequent reasoning.
  • Deep Knowledge — A representation of information about the internal and causal structure of a system that considers the interactions among its components.
  • Deep Representation — A model that captures all the forms of knowledge used by experts used in their reasoning. Domain — An area of expertise. An area of applicability.
  • Dynamic Explanation — In expert systems, an explanation facility that reconstructs the reasons for its actions as it evaluates results.
  • Expert — A human being who has developed a high level of proficiency in making judgements in a specific, usually narrow, domain.
  • Expert System (ES) — A computer system that applies reasoning methodologies using knowledge in a specific domain to render advice or recommendations, much like a human expert. A computer system that achieves a high level of performance in task areas, that for human beings, require years of special education and training.
  • Expert System Shell — A computer program that facilitates the relatively easy implementation of a specific expert system.
  • Expertise — The set of capabilities that underlies the performance of human experts, including extensive domain knowledge, heuristic rules that simplify and improve approaches to problem solving, meta-knowledge and metacognition, and compiled forms of behavior that afford great economy in skilled performance.
  • Firing a Rule — Obtaining information on either the IF or THEN part of a rule, which makes this rule an assertion (true or false).
  • Forward Chaining — Data-driven search in a rule based system.
  • Fuzzy Logic — Ways of reasoning that can cope with uncertain or partial information; characteristic of human thinking and many expert systems.
  • Fuzzy Sets — A set theory approach in which set membership is less precise than having objects be strictly in or out of the set (as in Boolean logic).
  • Genetic Algorithms — Software programs that learn in an evolutionary manner, similar to the way biological system evolve. Genetic
  • Programming — The extension of the genetic algorithm model of learning into the space of programs. That is, the objects that constitute the population are not fixed-length character strings that encode possible solutions to the problem at hand, they are programs that, when executed, "are" the candidate solutions to the problem.
  • Goal-seeking Analysis — The capability of asking the computer what values certain variables must have in order to attain desired goals.
  • Heuristics — Informal, judgmental knowledge of an application area that constitutes the “rules of good judgement” in the field. Heuristics also encompasses the knowledge of how to plan steps in solving a complex problem, how to improve performance.
  • Heuristic Programming — The use of heuristics in problem solving.
  • Hierarchical Reasoning — A method, based on tree search in which certain alternatives, objects or events can be eliminated at various levels of the search hierarchy.
  • IF-THEN — A conditional rule in which certain action is taken only if some condition is satisfied.
  • Induction Table — A table that facilitates rule induction for expert systems.
  • Inductive Learning — A machine learning approach in which rules are inferred from facts or data.
  • Inductive Reasoning — In logic, reasoning from the specific to the general Conditional or antecedent reasoning.
  • Inexact (Approximate) Reasoning — Used when the expert system must make decisions based on partial or incomplete information.
  • Inference — The process of drawing a conclusion from given evidence. To reach a decision by reasoning.
  • Inference Engine — That part of an expert system that actually performs the reasoning function.
  • Inference Rules — Rules in expert systems which direct the inference engine.
  • Information— Data that are organized in a meaningful way. Intelligence — The capability of a system to adapt its behavior to meet its goals in a range of environments.
  • Intelligent Agent (IA) — Expert or knowledge-based system that is embedded in computer-based information systems (or their components) to make them smarter.
  • Intelligent Database — A database management system that exhibits artificial intelligence features to assist the user; and often includes expert systems and intelligent agents.
  • Knowledge — Understanding, awareness, or familiarity acquired through education or experience. Anything that has been learned, perceived, discovered, inferred, or understood. The ability to use information.
  • Knowledge Acquisition — The extraction and formulation of knowledge derived from various sources, especially from experts.
  • Knowledge Base — A collection of facts, rules, and procedures organized into schemas. The assembly of all of the information and knowledge of a specific field of interest.
  • Knowledge-based System (KBS) — Typically a rule-based system for providing expertise. Identical to expert systems, except that the source of expertise may include documented knowledge.
  • Knowledge Discovery — A machine learning process that performs rule induction, or, a related procedure to establish knowledge from large databases or textual sources.
  • Knowledge Management — The active management of expertise in an organization. It involves collecting, categorizing, and disseminating knowledge.
  • Knowledge Map— See Induction Table.
  • Knowledge-poor Procedures — Standard methods for dealing with shallow knowledge domains.
  • Knowledge Representation — A formalism for representing facts and rules in the computer about a subject or specialty.
  • Machine Learning — A process used by computer that can learn from experience or past example.
  • Meta-knowldge — Knowledge in an expert system about how the system operates or reasons. More generally, knowledge about knowledge.
  • Modus Ponens — An inference rule type which from ”A implies B” justifies B by the existence of A.
  • Modus Tollens — An inference rule type in which a rule “A implies B” may be true, but B is known to be false, implying that A is false.
  • Natural Language Processing (NLP) — Use of a natural language processor to interface with a computer based system.
  • Neural Computing (Networks) — An experimental computer design that aims at building intelligent computers that operate in manner modeled on the human brain.
  • Neuron — A cell (processing element) of a biological or artificial neural network.
  • Pattern Matching — See Pattern Recognition. However, sometimes it refers specifically to matching the IF and THEN parts in rule-based systems. In this case, pattern matching can be considered as one are of pattern recognition.
  • Pattern Recognition— A technique of matching an external pattern to one stored in a computers memory; used in inference engines, image processing, neural computing, and speech recognition ( in other words, the process of classifying data into predetermined categories.
  • Predicate Logic (Calculus) — A logical system of reasoning used in AI programs to indicate relationships among data items.
  • Procedural Knowledge — Information about courses of action.
  • Procedural Rules — Rules that advise on how to solve a problem, given that certain facts are known.
  • Production Rules — A knowledge representation method in which knowledge is formalized into “rules” containing an IF part and a THEN part (also called a condition and an action).
  • Propositional Logic — A formal logical system of reasoning in which conclusions are drawn from a series of statements according to a strict set of rules.
  • Qualitative Reasoning — A means of representing and making inferences using general, physical knowledge about the world.
  • Reproduction — The creation of new generation of improved solutions by a genetic algorithm.
  • Rule — A formal way of specifying a recommendation, directive, or strategy, expressed as IF premise THEN conclusion, and possibly an ELSE conclusion.
  • Rule-based System — A system in which knowledge is represented completely in terms of rules (e.g., a system based on production rules).
  • Rule Induction — Rules are created by a computer from examples of problems where the outcome is known in a process called induction. These rules are generalized to other case;
  • Schema — A data structure for knowledge representation. Examples of schemas are frames and rules.
  • Search Space — Set of all possible solutions to a problem;
  • Search Tree — Graphic presentation that shows the problem, its alternative solutions, and the progress of a search for the best (acceptable) solution.
  • Self-organizing — A neural network architecture that uses unsupervised learning.
  • Semantic Network — A knowledge representation method consisting of a network of nodes, representing concepts or objects, connected by arcs describing the relations between the nodes.
  • Semantics — The meaning in language. The relationship between words and sentences.
  • Shallow Knowledge — A representation of “surface-level” information that can be used to deal with very specific situations.
  • Shallow (Surface) Representation — Model that does not capture all of the forms of knowledge used by experts in their reasoning. Contrasted with Deep Representation.
  • Soft Information — Fuzzy, unofficial, intuitive, subjective, nebulous, implied, and vague information.
  • Supervised Learning — A method of training artificial neural networks in which sample cases are shown to the network as input, and the weights are adjusted to minimize the error in its outputs.
  • Symbol — A string of characters that represents some real world concept.
  • Symbol Structures — The meaningful relationships represented in an AI program
  • Symbolic Processing — The use of symbols, rather than numbers, combined with rules of thumb (i.e. heuristics), to process information and solve problems.
  • Syntax — The manner in which words are assembled to form phrases and sentences. Putting words in specific order.
  • System — A set of elements that is considered to act as a single, goal-oriented entity.
  • Uncertainty — In the context of expert systems, uncertainty refers to a value that cannot be determined during a consultation. Many expert systems can accommodate uncertainty.
  • Unsupervised Learning — A method of training artificial neural networks in which only input stimuli are shown to the network, which is self-organizing.
  • Weights — Values assigned on each connection at the input to a neuron. Analogous to a synapse in the brain. Weights control the inflow to the processing elements in neural network

References & Resources

  • What is AI?