A hub of online professional and topical glossaries/dictionaries
Items 1→50 of 82. Page 1 of 2. items/page.
ACTION-BASED PLANNING  look up translate image
The goal of action-based planning is to determine how to decompose a high level action into a network of subactions that perform the requisite task. Therefore the major task within such a planning system is to manage the constraints that apply to the interrelationships (e.g., ordering constraints) between actions. In fact, action-based planning is best viewed as a constraint satisfaction problem. The search for a plan cycles through the following steps: choose a constraint and apply the constraint...(more)
ADAPTIVE INTERFACE  look up translate image
A computer interface that automatically and dynamically adapts to the needs and competence of each individual user of the software.
AGENT ARCHITECTURE  look up translate image
There are two levels of agent architecture, when a number of agents are to work together for a common goal. There is the architecture of the system of agents, that will determine how they work together, and which does not need to be concerned with how individual agents fulfil their sub-missions; and the architecture of each individual agent, which does determine its inner workings. The architecture of one software agent will permit interactions among most of the following components (depending...(more)
AGENTS  look up translate image
Agents are software programs that are capable of autonomous, flexible, purposeful and reasoning action in pursuit of one or more goals. They are designed to take timely action in response to external stimuli from their environment on behalf of a human. When multiple agents are being used together in a system, individual agents are expected to interact together as appropriate to achieve the goals of the overall system. Also called autonomous agents, assistants, brokers, bots, droids, intelligent agents, software agents.
AI EFFECT  look up translate image
The great practical benefits of AI applications and even the existence of AI in many software products go largely unnoticed by many despite the already widespread use of AI techniques in software. This is the AI effect. Many marketing people don't use the term "artificial intelligence" even when their company's products rely on some AI techniques. Why not? It may be because AI was oversold in the first giddy days of practical rule-based expert systems in the 1980s, with the peak perhaps marked by...(more)
AI LANGUAGES AND TOOLS  look up translate image
AI software has different requirements from other, conventional software. Therefore, specific languages for AI software have been developed. These include LISP, Prolog, and Smalltalk. While these languages often reduce the time to develop an artificial intelligence application, they can lengthen the time to execute the application. Therefore, much AI software is now written in languages such as C++ and Java, which typically increases development time, but shortens execution time. Also, to reduce...(more)
ALGORITHM  look up translate image
An algorithm is a set of instructions that explain how to solve a problem. It is usually first stated in English and arithmetic, and from this, a programmer can translate it into executable code (that is, code to be run on a computer).
The actual and potential applications are virtually endless. Reviewing Stottler Henke's work will give you some idea of the range. In general, AI applications are used to increase the productivity of knowledge workers by intelligently automating their tasks; or to make technical products of all kinds easier to use for both workers and consumers by intelligent automation of different aspects of the functionality of complex products.
ARTIFICIAL INTELLIGENCE  look up translate image
Artificial intelligence (AI) is the mimicking of human thought and cognitive processes to solve complex problems automatically. AI uses techniques for writing computer code to represent and manipulate knowledge. Different techniques mimic the different ways that people think and reason (see case-based reasoning and model-based reasoning for example). AI applications can be either stand-alone software, such as decision support software, or embedded within larger software or hardware systems. AI has...(more)
ASSOCIATIVE MEMORIES  look up translate image
Associative memories work by recalling information in response to an information cue. Associative memories can be autoassociative or heteroassociative. Autoassociative memories recall the same information that is used as a cue, which can be useful to complete a partial pattern. Heteroassociative memories are useful as a memory. Human long-term memory is thought to be associative because of the way in which one thought retrieved from it leads to another. When we want to store a new item of information...(more)
AUTOMATED DIAGNOSIS SYSTEMS  look up translate image
Most diagnosis work is done by expert humans such as mechanics, engineers, doctors, firemen, customer service agents, and analysts of various kinds. All of us usually do at least a little diagnosis even if it isn't a major part of our working lives. We use a range of techniques for our diagnoses. Primarily, we compare a current situation with past ones, and reapply, perhaps with small modifications, the best past solutions. If this doesn't work, we may run small mental simulations of possible solutions...(more)
AUTONOMOUS AGENTS  look up translate image
A piece of AI software that automatically performs a task on a human's behalf, or even on the behalf of another piece of AI software, so together they accomplish a useful task for a person somewhere. They are capable of independent action in dynamic, unpredictable environments. "Autonomous agent" is a trendy term that is sometimes reserved for AI software used in conjunction with the Internet (for example, AI software that acts as your assistance in intelligently managing your e-mail). Autonomous...(more)
BAYESIAN NETWORKS  look up translate image
A modeling technique that provides a mathematically sound formalism for representing and reasoning about uncertainty, imprecision, or unpredictability in our knowledge. For example, seeing that the front lawn is wet, one might wish to determine whether it rained during the previous night. Inference algorithms can use the structure of the Bayesian network to calculate conditional probabilities based on whatever data has been observed (e.g., the street does not appear wet, so it is 90% likely that...(more)
CASE-BASED REASONING  look up translate image
Case-based reasoning (CBR) solves a current problem by retrieving the solution to previous similar problems and altering those solutions to meet the current needs. It is based upon previous experiences and patterns of previous experiences. Humans with years of experience in a particular job and activity (e.g., a skilled paramedic arriving on an accident scene can often automatically know the best procedure to deal with a patient) use this technique to solve many of their problems. One advantage...(more)
CLASSIFICATION  look up translate image
Automated classification tools such as decision trees have been shown to be very effective for distinguishing and characterizing very large volumes of data. They assign items to one of a set of predefined classes of objects based on a set of observed features. For example, one might determine whether a particular mushroom is "poisonous" or "edible" based on its color, size, and gill size. Classifiers can be learned automatically from a set of examples through supervised learning. Classification...(more)
CLUSTERING  look up translate image
Clustering is an approach to learning that seeks to place objects into meaningful groups automatically based on their similarity. Clustering, unlike classification, does not require the groups to be predefined with the hope that the algorithm will determine useful but hidden groupings of data points. The hope in applying clustering algorithms is that they will discover useful but unknown classes of items. A well-publicized success of a clustering system was NASA's discovery of a new class of stellar spectra. See IQE, GIIF, WebMediator, Rome Graphics, and data mining for examples of applications that use clustering.
COGNITIVE SCIENCE  look up translate image
Artificial intelligence can be defined as the mimicking of human thought to perform useful tasks, such as solving complex problems. This creation of new paradigms, algorithms, and techniques requires continued involvement in the human mind, the inspiration of AI. To that end, AI software designers team with cognitive psychologists and use cognitive science concepts, especially in knowledge elicitation and system design.
COGNITIVE TASK ANALYSIS  look up translate image
Cognitive task analysis (CTA) is a systematic process by which the cognitive elements of task performance are identified. This includes both domain knowledge and cognitive processing. Thus, CTA focuses on mental activities that cannot be observed and is in contrast to behavioral task analysis that breaks the task down into observable, procedural steps. CTA is most useful for highly complex tasks with few observable behaviors. Examples of cognitive processing elements include: to decide, judge, notice,...(more)
COLLABORATIVE FILTERING  look up translate image
A technique for leveraging historical data about preferences of a body of users to help make recommendations or filter information for a particular user. Intuitively, the goal of these techniques is to develop an understanding of what may be interesting to a user by uncovering what is interesting to people who are similar to that user. See GIIF and IQE for examples of applications that use collaborative filtering techniques.
COMMONSENSE REASONING  look up translate image
Ordinary people manage to accomplish an extraordinary number of complex tasks just using simple, informal thought processes based on a large amount of common knowledge. They can quickly plan and undertake a shopping expedition to six or seven different shops, as well as pick up the kids from soccer and drop a book back at the library, quite efficiently without logically considering the hundreds of thousands of alternative ways to plan such an outing. They can manage their personal finances, or find...(more)
COMPUTER VISION  look up translate image
Making sense of what we see is usually easy for humans, but very hard for computers. Practical vision systems to date are limited to working in tightly controlled environments. Synonym: machine vision
CONSTRAINT SATISFACTION  look up translate image
Constraints are events, conditions or rules that limit our alternatives for completing a task. For example, the foundation of a building has to be laid before the framing is done; a car has to be refueled once every four hundred miles, a neurosurgeon is needed to perform brain surgery, or a Walkman can only operate on a 9-volt battery. Satisfying constraints is particularly important in scheduling complex activities. By first considering applicable constraints, the number of possible schedules...(more)
DATA FUSION  look up translate image
Information processing that deals with the association, correlation, and combination of data and information from single and multiple sources to achieve a more complete and more accurate assessment of a situation. The process is characterized by continuous refinement of its estimates and assessments, and by evaluation of the need for additional sources, or modification of the process itself, to achieve improved results.
DATA MINING  look up translate image
The non-trivial process of uncovering interesting and useful relationships and patterns in very large databases to guide better business and technical decisions. Data mining is becoming increasingly important due to the fact that all types of commercial and government institutions are now logging huge volumes of data and now require the means to optimize the use of these vast resources. The size of the databases to which data mining techniques are applied is what distinguishes them from more traditional...(more)
DECISION AIDS  look up translate image
Software that helps humans make decisions, particularly about complex matters when a high degree of expertise is needed to make a good decision.
DECISION SUPPORT  look up translate image
Decision support is a broad class of applications for artificial intelligence software. There are many situations when humans would prefer machines, particularly computers, to either automatically assist them in making decisions, or actually make and act on a decision. There are a wide range of non-AI decision support systems such as most of the process control systems successfully running chemical plants and power plants and the like under steady state conditions. However, whenever situations become...(more)
DECISION THEORY  look up translate image
Decision theory provides a basis for making choices in the face of uncertainty, based on the assignment of probabilities and payoffs to all possible outcomes of each decision. The space of possible actions and states of the world is represented by a decision tree.
DECISION TREES  look up translate image
A decision tree is a graphical representation of a hierarchical set of rules that describe how one might evaluate or classify an object of interest based on the answers to a series of questions. For instance, a decision tree can codify the sequence of tests a doctor might take in diagnosing a patient. Such a decision tree will order the tests based on their importance to the diagnostic task. The result of each successive test dictates the path you take through the tree and therefore the tests...(more)
DECISION-CENTERED DESIGN  look up translate image

DEPENDENCY MAINTENANCE  look up translate image
Dependency maintenance is the technique of recording why certain beliefs are held, decisions were made, or actions were taken, in order to facilitate revising those decisions, actions, or beliefs in the face of changing circumstances. Several families of truth maintenance systems have been developed to facilitate dependency maintenance in particular kinds of situations (e.g. need to consider many alternate scenarios versus a single scenario, frequency with which assumptions change, etc).
DOCUMENT CLUSTERING  look up translate image
With document clustering techniques, documents can be automatically grouped into meaningful classes so that users of a database of full-text documents can easily search through related documents.Finding individual documents from amongst large on-line, full-text collections has been a growing problem in recent years due to the falling price of computer storage capacity and the networking of document databases to large numbers of people. Traditional library indexing has not provided adequate information...(more)
DOMAIN  look up translate image
An overworked word for AI people. "Domain" can mean a variety of things including a subject area, field of knowledge, an industry, a specific job, an area of activity, a sphere of influence, or a range of interest, e.g., chemistry, medical diagnosis, putting out fires, operating a nuclear power plant, planning a wedding, diagnosing faults in a car. Generally, a domain is a system in which a particular set of rules, facts, or assumptions operates. Humans can usually easily figure out what's meant...(more)
DOMAIN EXPERT  look up translate image
The person who knows how to perform an activity within the domain, and whose knowledge is to be the subject of an expert system. This person's or persons' knowledge and method of work are observed, recorded, and entered into a knowledge base for use by an expert system. The domain expert's knowledge may be supplemented by written knowledge contained in operating manuals, standards, specifications, computer programs, etc., that are used by the experts. Synonym: subject-matter expert (SME).
EMERGENCE  look up translate image
Emergence is the phenomenon of complex patterns of behavior arising out of the myriad interactions of simple agents, which may each operate according to a few simple rules. To put it another way, an emergent system is much more than simply the sum of its parts. It can happen without any grand master outside the system telling the individual agents how to behave. For example, all the people in a modern city acting in their individual capacities as growers, processors, distributors, sellers, buyers,...(more)
EXPERT SYSTEM  look up translate image
An expert system encapsulates the specialist knowledge gained from a human expert (such as a bond trader or a loan underwriter) and applies that knowledge automatically to make decisions. For example, the knowledge of doctors about how to diagnose a disease can be encapsulated in software. The process of acquiring the knowledge from the experts and their documentation and successfully incorporating it in the software is called knowledge engineering, and requires considerable skill to perform successfully....(more)
FUZZY LOGIC  look up translate image
Traditional Western logic systems assume that things are either in one category or another. Yet in everyday life, we know this is often not precisely so. People aren't just short or tall, they can be fairly short or fairly tall, and besides we differ in our opinions of what height actually corresponds to tall, anyway.. The ingredients of a cake aren't just not mixed or mixed, they can be moderately well mixed. Fuzzy logic provides a way of taking our commonsense knowledge that most things are a...(more)
FUZZY SETS  look up translate image
To be added
GAME THEORY  look up translate image
Game theory is a branch of mathematics that seeks to model decision making in conflict situations.
GENETIC ALGORITHMS  look up translate image
Search algorithms used in machine learning which involve iteratively generating new candidate solutions by combining two high scoring earlier (or parent) solutions in a search for a better solution. So named because of its reliance on ideas drawn from biological evolution.
GRANULARITY  look up translate image
Refers to the basic size of units that can be manipulated. Often refers to the level of detail or abstraction at which a particular problem is analyzed. One characteristic of human intelligence, Jerry R. Hobbs has pointed out, is the ability to conceptualize a world at different levels of granularity (complexity) and to move among them in considering problems and situations. The simpler the problem, the coarser the grain can be and still provide effective solutions to the problem.
HETEROGENEOUS DATABASES  look up translate image
Databases that contain different kinds of data, e.g, text and numerical data.
HEURISTIC  look up translate image
An heuristic is commonly called a rule of thumb. That is, an heuristic is a method for solving a problem that doesn't guarantee a good solution all the time, but usually does. The term is attributed to the mathematician, George Polya. An example of an heuristic would be to search for a lost object by starting in the last place you can remember using it.
HUMAN-CENTERED COMPUTING  look up translate image
Computers and other machines should be designed to effectively serve people's needs and requirements. All too often they're not. Commonly cited examples of this are the difficulty people have in setting up their VCR to record a TV show; and the difficulties people have in setting up a home computer facility, or hooking up to the Internet. Artificial intelligence software can be used to deliver more human-centered computing, improving system usability, extending the powerfulness of human reasoning...(more)
HYBRID SYSTEMS  look up translate image
Many of Stottler Henke's artificial intelligence software applications use multiple AI techniques in combination. For example, case-based reasoning may be used in combination with model-based reasoning in an automatic diagnostic system. Case-based reasoning, which tends to be less expensive to develop and faster to run, may draw on an historical databases of past equipment failures, the diagnosis of those, and the repairs effected and the outcomes achieved. So CBR may be used to make most failure...(more)
INFERENCE ENGINE  look up translate image
The part of an expert system responsible for drawing new conclusions from the current data and rules. The inference engine is a portion of the reusable part of an expert system (along with the user interface, a knowledge base editor, and an explanation system), that will work with different sets of case-specific data and knowledge bases.
INFORMATION FILTERING  look up translate image
An information filtering system sorts through large volumes of dynamically generated information to present to the user those nuggets of information which are likely to satisfy his or her immediate needs. Information filtering overlaps the older field of information retrieval, which also deals with the selection of information. Many of the features of information retrieval system design (e.g. representation, similarity measures or boolean selection, document space visualization) are present in information...(more)
INTELLIGENT TUTORING SYSTEMS  look up translate image
encode and apply the subject matter and teaching expertise of experienced instructors, using artificial intelligence (AI) software technologies and cognitive psychology models, to provide the benefits of one-on-one instruction -- automatically and cost-effectively. These systems provide coaching and hinting, evaluate each student's performance, assess the student's knowledge and skills, provide instructional feedback, and select appropriate next exercises for the student. See Stottler Henke case studies.
KAPPA  look up translate image
Rule-based object-oriented expert system tool and application developer (IntelliCorp Inc.). KAPPA is written in C, and is available for PCs. See AI Languages and Tools.
KNOWLEDGE ELICITATION  look up translate image
Synonym: knowledge acquisition.
KNOWLEDGE ENGINEERING  look up translate image
Knowledge engineering is the process of collecting knowledge from human experts in a form suitable for designing and implementing an expert system. The person conducting knowledge engineering is called a knowledge engineer.
first prev Page of 2 next last
Back to Top
Glossary of AI terms
Visibility Public
Created by admin
Created on 2012-07-28 00:18:15
Number of terms 82
Last added None