ITGS Syllabus

Friday, December 08, 2006

Topic 182

key terms—AI, Turing test, parallel processing, machine learning, natural language, common-sense knowledge, agent, pattern recognition, expert system, knowledge base, inference engine, heuristics, fuzzy logic, knowledge engineer, domain by Tommy

AI – AI stands for artificial intelligence. It is defined as the ability of a computer or other machine to perform actions which normally require intelligence. This includes simulating moves for a computer chess game, or even speaking to humans, as in a chat bot.

Turing Test – A Turing test is a test of whether a computer’s intelligence is humanlike or not. The test is performed by having a panel of humans “talk to” a computer. If they believe that the computer is really a human, then the computer is said to have passed the Turing Test.

Parallel Processing – Parallel processing is when more than one computer is working on the same or multiple tasks at the same time. For example, if a problem or task is too big for one computer to handle, more computers can work on different parts of it so that the task can get done faster.

Machine Learning – Machine learning is much like the way living things learn, except with machines. Through machine learning, machines can improve their performance on future tasks based on what they did in the past. They are able to remember which ways are most efficient and which are least efficient, and which ones do not work at all.

Natural Language – Natural language is any language spoken by humans. The opposite of this is programming language or computer language, which is not as complex as human language. Computers are not able to understand things like philosophy because they cannot understand natural language.

Common-Sense Knowledge – Common sense knowledge is the knowledge that humans have without having to be told. Humans are able to deduce things like “if I drop this ball, it will fall” without being taught. However, computers do not have this ability and must be programmed so that they know that the ball will drop.

Agent – In a client-server exchange, the agent is the part of the system that does the transferring and packaging of information.

Pattern Recognition – Pattern recognition is the ability to classify and arrange knowledge according to certain characteristics of that knowledge. An example of pattern recognition in computers today is with spyware. Spyware programs monitor the sites that users visit, try to find patterns in them, and then show advertisements that fit the category of what users look at.

Expert System – The expert system is a system that attempts to provide solutions to problems in a particular field, based on a database of information about that field. An expert system might specialize in biology and be able to provide answers to questions about biology, and even carry out complex thought processes on questions relating to biology.

Knowledge Base – The knowledge base is the part of the expert system that contains all the facts and information that it needs to give solutions and solve problems.

Inference Engine – In inference engine is the part of an expert system that draws inferences and deduces new facts by using old knowledge.

Fuzzy Logic – Fuzzy logic is a type of algebra in which a range of values ranging from “true” to “false” are employed. It is mainly used in making decisions where data is not very precise, in order to come up with an approximate answer instead of an exact one.

Knowledge Engineer – A knowledge engineer is someone who builds and designs expert systems.

Domain – A domain is a group of networked computers that share a common IP address.


key terms—AI, Turing test, parallel processing, machine learning, natural language, common-sense knowledge, agent, pattern recognition, expert system, knowledge base, inference engine, heuristics, fuzzy logic, knowledge engineer, domain by Tanay

key terms—AI, Turing test, parallel processing, machine learning, natural language, common-sense knowledge, agent, pattern recognition, expert system, knowledge base, inference engine, heuristics, fuzzy logic, knowledge engineer, domain

AI - the branch of computer science that deal with writing computer programs that can solve problems creatively; "workers in AI hope to imitate or duplicate intelligence in computers and robots.

Turing test - The Turing test is a proposal for a test of a machine's capability to perform human-like conversation. Described by Alan Turing in the 1950 paper "Computing machinery and intelligence", it proceeds as follows: a human judge engages in a natural language conversation with two other parties, one a human and the other a machine

Parallel processing - is an efficient form of information processing that emphasizes the exploitation of concurrent events in the computing process. Concurrency implies parallelism, simultaneity and pipelining. Parallel events may occur in multiple resources during the same time instant; pipelined events are attainable in a computer system at various processing levels.

Machine Learning – is an area of artificial intelligence concerned with the development of techniques which allow computers to "learn". More specifically, machine learning is a method for creating computer programs by the analysis of data sets.

Natural Language - A type of search which allows the user to present their search as a question or statement instead of restricting it to only important words or phrases, as in Keyword or Controlled Vocabulary searches. Available in certain databases only. (Unit 4> A Primer on Databases and Catalogs)

Common-sense Knowledge - A form of evidence that is based on conventional wisdom, tradition, or someone’s personal philosophy or perspective. It is hard to judge the validity and reliability of common sense because little supporting evidence is involved. Most people judge the validity and reliability of common sense by the person citing common sends as the basis for a decision.

Agent - are search tools that automatically seek out relevant online information based on your specifications. Agent AKAs include: intelligent agent, personal agents, knowbots or droids.; A function that represents a requester to a server. An agent can be present in both a source and a target system.

Pattern Recognition – is a field within the area of machine learning and can be defined as "the act of taking in raw data and taking an action based on the category of the data"

Expert System – A software system with two basic components: a knowledge base and an inference engine. The system mimics an expert's reasoning process; computer with 'built-in' expertise, which, used by a non-expert in a particular subject area, can evaluate or make other decisions concerning that subject.

Knowledge Base – A store of knowledge about a domain represented in machine-processable form, which may be rules (in which case the knowledge base may be considered a rule base), facts, or other representations.

Inference Engine – That part of an expert system that actually performs the reasoning function.

Heuristics – Guidelines that a system administrator uses to intervene where the two-phase commit or abort would otherwise fail.; A problem-solving technique in which the most appropriate solution is selected using rules. Interfaces using heuristics may perform different actions on different data given the same command. All systems using heuristics are classified as intelligent.

Fuzzy Logic – A form of artificial intelligence, stored on a computer chip, that enables a camcorder or television to make complex adjustments in focus or picture quality based on ideal models.

Knowledge Engineer – An AI specialist responsible for the technical side of developing an expert system. The knowledge engineer works closely with the domain expert to capture the expert's knowledge in a knowledge base.

Domain - A group of computers and devices on a network that are administered as a unit with common rules and procedures. Within the Internet, domains are defined by the IP address. All devices sharing a common part of the IP address are said to be in the same domain.


key terms—AI, Turing test, parallel processing, machine learning, natural language, common-sense knowledge, agent, pattern recognition, expert system, knowledge base, inference engine, heuristics, fuzzy logic, knowledge engineer, domain by Matthew

AI, which stands for artificial intelligence, is generally understood as intelligence exhibited by a nonhuman entity. In the real world, AI is most often applied in the computer and robotics industry. An example of AI is optical character recognition AI, which is a type of computer software designed to distinguish certain texts.

Turing Test
A Turing test tests a machine's ability to perform conversation with a human. A Turing test is usually made up of two people, with one being the judge that decides whether the machine has passed or failed. The judge has a conversation with the other person and the machine being tested. The three-way conversation is usually done with text rather than actual voices so that the judge is not able to know which of the two parties he or she is talking to is the machine.

Parallel Processing
Parallel processing is the ability of the brain or a machine to simultaneously process multiple things. Parallel processing is a rather complex process, especially in the brain. An example of this is vision. When your brain sees something, it divides the image into four components; color, motion, form, and depth. These are then analyzed and compared to memories, which helps the brain identify the image.

Machine Learning
Machine learning is associated with the development of techniques that allow a computer to learn things. In general, machine learning is understood as a subtopic of artificial intelligence and can be divided further into two categories, inductive and deductive. Machine learning is generally used to help with data mining and statistical analysis.

Natural Language
Natural language can be defined as a language that is spoken or written by humans for general-purpose communications. It should be noted that natural language is the opposite of programming language or language used to explain mathematical logic.

Common-Sense Knowledge
Common-sense knowledge is knowledge derived from common sense. It is often used to refer to certain experiences or understandings that most people would find in par with universal acceptance. It should be noted that computers do not have common-sense knowledge and must be programmed to have the knowledge humans are born with.

In technology, agents refer to technologies that help make tasks easier to complete for humans. An example of an agent is a robot.

Pattern Recognition
Pattern recognition is the act of taking in raw data and taking an action based on the category of the data. A good example of pattern recognition software is the fingerprint based security system. The system works by recognizing a person's fingerprint to that of a fingerprint stored in its memory.

Expert System
An expert system is a system that has some of the subject-specific knowledge that human experts of that subject would normally have. Expert systems are often used to help users of a certain program better understand how to use the program. Expert systems are sometimes called wizards.

Knowledge based
Knowledge base is simply a collection of information. An example of a knowledge base is Wikipedia, which is a collection of information posted by users on the internet.

Inference Engine
An inference engine is a computer program that creates answers based on information found in a knowledge base. It is one of the core parts of the expert system and is often considered the brain of the expert system because the inference engine makes all the final decisions and processes the final information before it reaches the user.

Fuzzy Logic
Fuzzy logic is a mathematical technique that deals with imprecise data and problems that have more than one solution. An example of a machine that uses fuzzy logic is an industrial clothes-washing machine. Using fuzzy logic systems, these machines detected and adapted to patterns of water movement during a wash cycle in order to decrease the consumption of water and increase efficiency.

Knowledge Engineer
Knowledge engineers are people who are trained in the field of expert systems. They help in breaking down information passed down by domain experts in order to easily communicate the information in more simplistic terms.

In software engineering, domain refers to a field of study that defines a set of common requirements, terminology, and functionality for any software program constructed to solve a problem in that field.


Post a Comment

<< Home