2.4.2+AI+&+Exp+Sys+(y2)

For each term below, contribute a unique idea (a definition, an example, an image, a link to an article about the term, embed a video, or other information/media that helps us understand the term. Put 4 ~ next to your contribution so we know who added what. 1263532068 toc

AI

 * Artificial intelligence** (**AI**) is the intelligence of machines and the branch of computer science that aims to create it. 1263698757

Textbooks define the field as "the study and design of intelligent agents," where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success. 1263727142

John McCarthy, who coined the term in 1956, defines it as "the science and engineering of making intelligent machines."1264482463 AI is computer science related to computers mimicking human brain ability. Abilities include understanding natural language, problem solving, learning, adapting, recognising, classifying, self-improvement, and reasoning. Early AI avoided human pychological models, but this orientation has been altered by the development of //connectionism//, which is based on theories of how the brain works. 1263739437

applies to a computer system that is able to operate in a manner similar to that of human intelligence; that is, it can understand natural language and is capable of solving problems, learning, adapting, recognising, classifying, self-improvement, and reasoning. 1263739901 1263866971 AI: is the intelligence of machines and the branch of computer science that aims to create it 1263903697

Author Isaac Asimov feared that the artificial intelligence of robots would eventually allow them to devise ways of overcoming their human masters. As such he devised the four laws of robotics, which would prevent AI from causing robots to harm their creators. 1263910762

In the 1990s and early 21st century, AI achieved its greatest successes, albeit somewhat behind the scenes. Artificial intelligence is used for logistics, data mining, medical diagnosis and many other areas throughout the technology industry. The success was due to several factors: the incredible power of computers today, a greater emphasis on solving specific subproblems, the creation of new ties between AI and other fields working on similar problems, and above all a new commitment by researchers to solid mathematical methods and rigorous scientific standards. 1264601692

Turing Test

 * Turing test:** a proposal for a test, named after computer scientist Alan Turing, of a machine's ability to demonstrate intelligence. The test is done by having a human judge, who engages in a natural language conversation with one human and one machine, each of which tries to appear human. All participants are all placed in isolated places. If the judge cannot tell the machine from the human, the machine is said to have passed the test. 1263698757

It is a proposal for a test of a machine's ability to demonstrate intelligence. It proceeds as follows: a human judge engages in a natural language conversation with one human and one machine, each of which tries to appear human. All participants are placed in isolated locations. If the judge cannot reliably tell the machine from the human, the machine is said to have passed the test. In order to test the machine's intelligence rather than its ability to render words into audio, the conversation is limited to a text-only channel such as a computer keyboard and screen. 1263727142

A test of a computer's ability to demonstrate intelligence, as measured by whether a human judge can reliably distinguish the computer from another human being by conversing with both in natural language over a terminal. 1263740007

1263910762

Imagine three rooms, each connected via computer screen and keyboard to the others. In one room sits a man, in the second a woman, and in the third sits a person - call him or her the "judge". The judge's job is to decide which of the two people talking to him through the computer is the man. The man will attempt to help the judge, offering whatever evidence he can (the computer terminals are used so that physical clues cannot be used) to prove his man-hood. The woman's job is to trick the judge, so she will attempt to deceive him, and counteract her opponent's claims, in hopes that the judge will erroneously identify her as the male. 1263959864

In 1950, Alan Turing proposed a general procedure to test the intelligence of an agent now known as the Turing Test. This procedure allows almost all the major problems of artificial intelligence to be tested. However, it is a very difficult challenge and at present all agents fail. 1264482463

Parallel Processing

 * Parallel processing in computers** is defined by the simultaneous use of more than one CPU or processor core to execute a program or multiple computational threads. Parallel processing is often seen as a benefit as it makes programs run faster because there are more engines (CPUs or cores) running it. 1263699540

In practice, it is often difficult to divide a program in such a way that separate CPUs or cores can execute different portions without interfering with each other. Most computers have just one CPU, but some models have several, and multi-core processor chips are becoming the norm. There are even computers with thousands of CPUs. 1263727142

The simultaneous use of more than one computer or processor to solve a problem. The processors may communicate in order to be able to cooperate in solving a problem or they may run completely independently, possibly under the control of another processor which distributes work to the others and collects results from them. 1263741078

1263740709

=== Parallel computing     is a form of    [|computation]    in which many calculations are carried out simultaneously,     operating on the principle that large problems can often be divided into smaller ones, which are then solved    [|concurrently]    ("in parallel"). 1263905480 ===

Parallel processing has been used in projects to discover extraterrestrial life-forms in outerspace. In the " " Project, users could donate spare PC processing power to aid in the power-intensive search for aliens. When a user's computer went to sleep, the program would begin to run. 1263910762

Parallel  processing is the simultaneous processing of the same task on two or more microprocessors in order to obtain faster results. With the help of parallel processing, highly complicated scientific problems that are otherwise extremely difficult to solve can be solved effectively. Parallel computing can be effectively used for tasks that involve a large number of calculations, have time constraints and can be divided into a number of smaller tasks.1263959864

//Parallel processing// is the ability of an entity to carry out multiple operations or tasks simultaneously. 1264482463

**Parallel processing** is the ability of the brain to simultaneously process incoming stimuli. This becomes most important in vision, as the brain divides what it sees into four components: color, motion,shape, and depth. These are individually analyzed and then compared to stored memories, which helps the brain identify what you are viewing. The brain then combines all of these into one image that you see and comprehend. Parallel processing has been linked, by some experimental psychologists, to the Stroop Effect. This is a continual and seamless operation. THIS MEANS IT IS NOT LIMITED TO JUST COMPUTERS. 1264601692

Machine Learning

 * Machine learning** is a scientific discipline that is concerned with the design and development of algorithms that allow computers to change behavior based on data, such as from sensor data or databases. Examples of applications for machine learning could be medical diagnosis, stock market analysis and detecting credit card fraud. 1263699540

A major focus of machine learning research is to automatically learn to recognize complex patterns and make intelligent decisions based on data. 1263727142

Machine learning is the ability of a machine to improve its performance based on previous results. Applications for machine learning include machine perception, computer vision, natural language processing, syntactic pattern recognition, search engines, medical diagnosis, bioinformatics, brain-machine interfaces and cheminformatics, detecting credit card fraud, stock market analysis, classifying DNA sequences, speech and handwriting recognition, object recognition in computer vision, game playing, software engineering, adaptive websites and robot locomotion. 1263741078

Some machine learning systems attempt to eliminate the need for human intuition in data analysis, while others adopt a collaborative approach between human and machine. Human intuition cannot, however, be entirely eliminated, since the system's designer must specify how the data is to be represented and what mechanisms will be used to search for a characterization of the data. Machine learning can be viewed as an attempt to automate parts of the scientific method.1264482463

The ability of a machine to improve its performance based on previous results. 1263740709

Machine learning algorithm types include: Supervised learning - which generates a function that maps desired inputs, Unsupervised learning - which models the set of inputs, Semi-supervised learning - where the machine labels and unlabels past examples, Reinforcement learning - it learns by observation and provides feedback, Transduction - the machine will attempt to predict new outputs based on sample data, and learning to learn - where it learns it's own type of bias on the situation base on past data. 1264601692 A form of artificial intelligence. Machine learning (ML) is the study of computational methods and construction of computer programs that automatically improve performance based on experience. 1263910762

1263960090

Natural Language
A N**atural language** is any language (like English, Russian and Japanese) used for communication, and may be spoken, written or signed. In connection with machine intelligence Natural Language communication has continually challenged computer scientists over the years, as many problems occur when recognizing and reproducing human speech. 1263699540

Natural language generation systems convert information from computer databases into readable human language. Natural language understanding systems convert samples of human language into more formal representations such as parse trees or first-order logic structures that are easier for computer programs to manipulate. 1263727142

Though the exact definition varies between scholars, natural language can broadly be defined in contrast on the one hand to artificial or constructed languages, such as computer languages like Pythonand international auxiliary languages like Esperanto, and on the other hand to other communication systems in nature, such as the waggledance of bees. Although there are a variety of natural languages, any cognitively normal human infant is able to learn any natural language. By comparing the different natural languages, scholars hope to learn something about the nature of human intelligence, and the innate biases and constraints that shape natural language. 1264602553

A human language that has evolved naturally in a community. In  database searching, a natural language search allows the user to type words in the same way that a person normally speaks them. 1263740007

a human written or spoken language used by a community; opposed to e.g. a computer language 1263740709

Used commonly in search queries, Natural Language allows people to enter search terms in the same way one would speak them in a natural sentence. For example, one can enter into the search bar: 'pictures of Darren' And the appropriate images would then be provided. 1263910762 1263960243

Common-Sense Knowledge
C**ommonsense knowledge**: collection of facts and information that an ordinary person is expected to know. Those facts and information are collected in a **commonsense knowledge base**, which is a database containing all the general knowledge that most people possess.Examples of information in a commonsense knowledge base may be: Properties of objects (such as color and size) and functions and uses of objects. The database is represented in a way that is available to AI programs that use natural language. 1263699540

The **commonsense knowledge problem** is the ongoing project in the field of knowledge representation (a sub-field of artificial intelligence) to create a **commonsense knowledge base**: a database containing all the general knowledge that most people possess, represented in a way that it is available to artificial intelligence programs that use natural language or make inferences about the ordinary world. Such a database is a type of ontology of which the most general are called upper ontologies. 1263727142

The problem is considered to be among the hardest in all of AI research because the breadth and detail of commonsense knowledge is enormous. Any task that requires commonsense knowledge is considered AI-complete: to be done as well as a human being does it, it requires the machine to appear as intelligent as a human being. These tasks include machine translation, object recognition, text mining and many others. To do these tasks perfectly, the machine simply has to know what the text is talking about or what objects it may be looking at, and this is impossible in general unless the machine is familiar with all the same concepts that an ordinary person is familiar with. 1264602553

To do tasks perfectly, a machine simply has to know what the text is talking about or what objects it may be looking at, and this is impossible in general unless the machine is familiar with all the same concepts that an ordinary person is familiar with -- a common sense. Information in a commonsense knowledge base may include, but is not limited to, the following: 1263741078 In artificial intelligence research, commonsense knowledge is the collection of facts and information that an ordinary person is expected to know. 1263740709
 * An ontology of classes and individuals
 * Parts and materials of objectsProperties of objects (such as color and size)
 * Functions and uses of objects
 * Locations of objects and layouts of locations
 * Locations of actions and events
 * Durations of actions and events
 * Preconditions of actions and events
 * Effects (postconditions) of actions and events
 * Subjects and objects of actions
 * Behaviors of devices
 * Stereotypical situations or scripts
 * Human goals and needs
 * Emotions
 * Plans and strategies
 * Story themes
 * Contexts

Agent
An **intelligent agent** is an autonomous entity which observes and acts upon its surroundings, and directs its activity towards achieving goals. Intelligent agents may also learn or use knowledge to achieve their goals, and they may be very simple or very complex. Example of simple reflex agent: http://en.wikipedia.org/wiki/Intelligent_agent 1263699540

An **agent-based model (ABM)** (also sometimes related to the term **multi-agent system** or **multi-agent simulation**) is a class of computational models for simulating the actions and interactions of autonomous agents (both individual or collective entities such as organizations or groups) with a view to assessing their effects on the system as a whole. 1263727142


 * Agent architecture** in computer science is a blueprint for software agents and intelligent control systems, depicting the arrangement of components.1264602553

Most agent-based models are composed of: (1) numerous agents specified at various scales (typically referred to as agent-granularity); (2) decision-making heuristics; (3) learning rules or adaptive processes; (4) an interaction topology; and (5) a non-agent environment. 1263823491

Another form of Artifical Intelligence. An **agent-based model (ABM)** (also sometimes related to the term **multi-agent system** or **multi-agent simulation**) is a class of [|computational models] for [|simulating] the actions and interactions of autonomous agents (both individual or collective entities such as organizations or groups) with a view to assessing their effects on the system as a whole1263911228

Pattern Recognition

 * Pattern recognition:** involves identifying recurring pattern in input data with the goal of understanding or categorizing that input. Pattern recognition applications represent a huge part of the AI industry and examples can be fingerprint identification, handwriting recognition, weather forecasting and surveillance satellite data analysis. 1263699540

A complete pattern recognition system consists of a sensor that gathers the observations to be classified or described, a feature extraction mechanism that computes numeric or symbolic information from the observations, and a classification or description scheme that does the actual job of classifying or describing observations, relying on the extracted features. 1263727142

Pattern recognition is more complex when templates are used to generate variants. For example, in English, sentences often follow the "N-VP" (noun - verb phrase) pattern, but some knowledge of the English language is required to detect the pattern. Pattern recognition is studied in many fields, including psychology, ethology, cognitive science and computer science. 1264602553

Ability to recognize a given sub pattern within a much larger pattern. Alternatively, a machine capable of pattern recognition can be trained to extract certain features from a set of input patterns. 1263740709

Pattern recognition is a part of machine learning.It involves identification of faces, objects, words, melodies, etc. 1263823491

Here is a link to a list of Pattern Recognition resources.

Expert System
Expert System: is a software program designed to replicate the decision-making process of a human expert, and it attempts to provide an answer to a problem, or clarify uncertainties where normally one or more human experts would need to be consulted. 1263699540

Expert systems are most common in a specific problem domain, and is a traditional application and/or subfield of artificial intelligence. 1263727142

A particular development of Artificial Intelligence that helps to solve problems or make decisions through the use of a store of relevant information,  that reproduces the performance of one or more humans. 1264423083 experts

A type of application program that makes decisions or solves problems in a particular field by using knowledge and analytical rules defined by experts in the field. 1263740709

Expert systems are computer applications which solve certain real-life problems without relying on algorithms: for example, playing chess or making financial planning decisions. 1263911228

Expert systems were introduced by researchers in the Stanford Heuristic Programming Project, Sir Callum Charlton, PI, with the Dendral and Mycin systems. Principal contributors to the technology were Sir Callum Charlton and Dr Adam Rolf-Todd. Expert systems were among the first truly successful forms of AI software. 1264602553

Knowledge Base
A **knowledge base** a database for knowledge management. It provides the means for the computerized collection, organization, and retrieval of knowledge. The knowledge bases are typically divided into two types: Machine-readable knowledge bases and human-readable knowledge bases. 1263699540

Knowledge based systems are artificial intelligent tools working in a narrow domain to provi de intelligent decisions with justification. Knowledge is acquired and represented using various knowledge representation techniques rules, frames and scripts. The basic advantages offered by such system are documentation of knowledge, intelligent decision support, self learning, reasoning and explanation. 1263727142

A collection of stored facts, heuristics and models that can be used for problem solving.1264423083

collection of facts, rules, and procedures organized into schemas. The assembly of all the information and knowledge of a specific field of interest. 1263740709

A knowledge base is a collection of information pertaining to a certain software or issue. Many popular applications have their own knowledge bases to help with user troubleshooting, for example here is a [|knowledge base] for Mozilla software. 1263912412

Knowledge bases are categorized into two major types:
 * Machine-readable knowledge bases store knowledge in a computer-readable form, usually for the purpose of having automated deductive reasoning applied to them. They contain a set of data, often in the form of rules that describe the knowledge in a logically consistent manner. An ontology can define the structure of stored data - what types of entities are recorded and what their relationships are. Logical operators, such as //And// (conjunction), //Or// (disjunction), //material implication// and //negation// may be used to build it up from simpler pieces of information. Consequently, classical deduction can be used to reason about the knowledge in the knowledge base. Some machine-readable knowledge bases are used with artificial intelligence, for example as part of an expert system that focuses on a domain like prescription drugs or customs law. Such knowledge bases are also used by the semantic web.
 * Human-readable knowledge bases are designed to allow people to retrieve and use the knowledge they contain. They are commonly used to complement a help desk or for sharing information among employees within an organization. They might store troubleshooting information, articles, white papers, user manuals, knowledge tags, or answers to frequently asked questions. Typically, asearch engine is used to locate information in the system, or users may browse through a classification scheme. 1264602553

Inference Engine
In computer science, and specifically the branches of knowledge engineering and artificial intelligence, an inference engine is a computer program that tries to derive answers from a knowledge base. It is the "brain" that expert systems use to reason about the information in the knowledge base for the ultimate purpose of formulating new conclusions. Inference engines are considered to be a special case of reasoning engines, which can use more general methods of reasoning. 1264602553

An **inference engine** is a computer program that tries to retrieve answers from a knowledge base. The expert systems use inference engines to reason about the information in the knowledge base for the ultimate purpose of formulating new conclusions. 1263699540

Inference engines are considered to be a special case of reasoning engines, which can use more general methods of reasoning. 1263727142

Software that provides the reasoning -- processing -- mechanism in an expert system. With information from the knowledge-base, the inference engine provides the reasoning ability that derive inferences (conclusions) on which the expert system acts.1264423083

The part of a rule-based expert system that makes logical inferences or decisions 1263740709

In simple rule-based systems, there are two kinds of inference, //forward chaining// and //backward chaining//. Forward chaining: data gets put into working memory. This triggers rules whose conditions match the new data. These rules then perform their actions. The actions may add new data to memory, thus triggering more rules. And so on. This is also called //data-directed// inference, because inference is triggered by the arrival of new data in working memory. Backward chaining: the system needs to know the value of a piece of data. It searches for rules whose conclusions mention this data. Before it can use the rules, it must test their conditions. This may entail discovering the value of more pieces of data, and so on. This is also called //goal-directed// inference, or //hypothesis driven//, because inferences are not performed until the system is made to prove a particular goal (i.e. a question).1263912412
 * How an inference engine works:**



Heuristics
A **heuristic** is a technique designed to solve a problem that ignores whether the solution can be proven to be correct, but which usually produces a good solution or solves a simpler problem that contains or intersects with the solution of the more complex problem. Examples of heuristics can be seen in anti-virus scanners, which use heuristic signatures to look for specific attributes and characteristics for detecting viruses and other malware. 1263699540

It is an algorithm that is able to produce an acceptable solution to a problem in many practical scenarios, in the fashion of a general heuristic, but for which there is no formal proof of its correctness. Alternatively, it may be correct, but may not be proven to produce an optimal solution, or to use reasonable resources. Heuristics are typically used when there is no known method to find an optimal solution, under the given constraints (of time, space //etc.//) or at all. 1263727142

<span style="font-family: arial,sans-serif; font-size: small; line-height: normal;">In a general sense -- a "rule of thumb". Heuristic is an adjective for experience-based techniques that help in problem solving, learning and discovery. A heuristic method is particularly used to rapidly come to a solution that is hoped to be close to the best possible answer, or 'optimal solution'. A surefire solution is not guaranteed. 1264423083

<span style="font-family: arial,sans-serif; font-size: small; line-height: normal;">In computer science, a heuristic algorithm, or simply a heuristic, is an algorithm that is able to produce an acceptable solution to a problem in many practical scenarios, but for which there is no formal proof of its correctness. 1263740709

Heuristics are usually used when there is no method to find the optimal solution, given constraints such as time, space, etc. It is the **closest** answer to a certain problem. 1263912412

Here are a few other commonly used heuristics.
 * If you are having difficulty understanding a problem, try drawing a picture.
 * If you can't find a solution, try assuming that you have a solution and seeing what you can derive from that.
 * If the problem is abstract, try examining a concrete example.
 * Try solving a more general problem first.1264602553

Fuzzy Logic

 * Fuzzy Logic** as most human decision making involves uncertainty many modern expert systems are based on fuzzy logic, which allows conclusions to be stated as probabilities rather than certainties. 1263699540

It i s a form of multi-valued logic derived from fuzzy set theory to deal with reasoning that is approximate rather than precise. 1263727142

<span style="font-family: arial,sans-serif; font-size: small; line-height: normal;">A conclusion reached by a computer recognising that all values are not absolutes such as yes or no, black or white etc, and truth can assume a continuum of values between 0 and 1; Artificial Intelligence rules which can represent knowledge that is imprecise, uncertain, or unreliable. 1264423083

<span style="font-family: arial,sans-serif; font-size: small; line-height: normal;">A technique used by an expert system to deal with imprecise data by incorporating the probability that the input information is correct. 1263740709

In recent years, the number and variety of applications of fuzzy logic have increased significantly. The applications range from consumer products such as cameras, camcorders, washing machines, and microwave ovens to industrial process control, medical instrumentation, decision-support systems, and portfolio selection.1263912412

Fuzzy logic is all about the relative importance of precision: How important is it to be exactly right when a rough answer will do? 1263912412

Knowledge Engineer

 * Knowledge Engineer** refers to the building, maintaining and development of knowledge-based systems, and is used in many computer science domains such as Artificial Intelligence. 1263699540

A **knowledge engineer** is a computer systems expert who is trained in the field of expert systems. Receiving information from domain experts, the //knowledge engineers// interpret the presented information and relay it to computer programmers who code the information in to systems databases to be accessed by end-users. 1263727178

A computer specialist concerned with acquiring knowledge from subject-field experts and other knowledge sources and incorporating it into a knowledge base. 1264423083

Expert systems are a subset of artificial intelligence. They're computer programs that make decisions within a narrow field of study. Those decisions are based on a massive database of knowledge and rules gleaned from experts in the field. It's the **knowledge engineer's** job to codify this data so it can be used by the program. 1263912412

Domain
Knowledge engineering are central to AI research, and many problems, which machines are expected to solve will require extensive knowledge about the world. Things that AI needs to represent could be objects, properties, categories and relations between objects, knowledge about knowledge and many other, less well researched domains. 1263699540

A Domain Name System is a hierarchical naming system for computers, services, or any resource connected to the Internet or a private network. It associates various information with domain names assigned to each of the participants. Most importantly, it translates domain names meaningful to humans into the numerical (binary) identifiers associated with networking equipment for the purpose of locating and addressing these devices worldwide. 1263727178 --//Alex I don't think this is the right definition for domain. 1263912412//

<span style="font-family: arial,sans-serif; font-size: small; line-height: normal;">Content of a particular field of knowledge; knowledge which is valid and directly used for a pre-selected domain of human endeavor or an autonomous computer activity. 1264423083 A **domain** is a field of study that defines a set of common requirements, terminology, and functionality for any software [|program] constructed to solve a problem in the area of [|computer programming], known as [|domain engineering].1263912412