3.11 Artificial Intelligence, Expert Systems and Robotics (J&Vonly)

Artificial Intelligence
Creating a system that produces results comparable to human intelligence.
Boolean logic
Logic in which clauses can have one of two states – such as yes or no, true or false.
CAPTCHA
a program that protects websites against bots by generating and grading tests that humans can pass but current computer programs cannot, such as text input or image selection
chaining
Use of logical statements to come to a conclusion.
computational intelligence
Approach that tries to create systems that think and learn in the same way humans do.
expert system shell
Software used to create expert systems.
expert systems
Software designed to make the same decisions that a human expert would, in a given knowledge domain.
feedback loop
Use of previous answers (right or wrong) to improve the decision making process next time.
fuzzy logic
Logic in which items can have multiple values, refers to degrees of truth, not True/false. Used in AI.
fuzzy set theory
System in which items can be partial or complete members of a set. Used in AI.
heuristics
General rules for performing a task, used to improve the perform of searching algorithms in AI applications.
IF-THEN rule
Rule used by the inference engine in an expert system to describe the relationship between key concepts.
inference engine
Part of an expert system which attempts to relate the users input with knowledge stored in the knowledge base.
inference rule
Rule used by the inference engine in an expert system to describe the relationship between key concepts. formulated by premises/arguments of if/then to infer a conclusion.
knowledge base
Area of an expert system where all facts about the knowledge domain are stored.
knowledge domain
Area of knowledge in which an expert system specialises.
knowledge engineer
Programmer responsible for entering expert knowledge into an expert system.
machine learning
Technique for making a computer produce better results by learning from past experiences and examples. Built on examination of large amounts of data and is able to react to new inputs.
machine translation
Technique for automatically translating one human language into another.
natural language processing
Techniques for processing human languages to enable a computer to understand their meaning.
neural networks
AI technique that tries to imitate the connections in the human brain, require training by trial and error before they become useful
pattern recognition
Computational Intelligence technique where computers are trained on examples and learn to recognise similarities between them.
speech recognition
Computer system that can process spoken language and understand its meaning.
training data
Example data used in a pattern recognition system.
Turing test
Proposed test to see if a computer is intelligent or not.
user interface
Part of an expert system that accepts users inputs and presents answers.
android
Robot designed to look like a human, with lifelike skin and other features.
autonomous
Robot which operates without human intervention.
sensors
Input devices used to measure physical traits, such as sound, heat, or light.
Natural Language
Refers to human language in contrast to artificial languages such as computer languages, how they (human languages) are interpreted by computers
Algorithm
Step by step instructions for performing an action or solving a problem, used by computers to process data, often includes decision trees.
Voice Recognition
voice is matched to words in a digital dictionary (uses digital patterns to identify the words), software can require training to understand a specific speaker
Robot
mechanical device controlled by a computer that interacts with the physical world. Can have a variety of output devices (tools, arms, etc) carries out series of complex (physical) actions. Can be autonomous, semi-autonomous or automatic.