Artificial Intelligence
- Created by: miacampbell31
- Created on: 28-03-22 11:46
View mindmap
- Artificial Intelligence
- - Considers all aspects of intelligence and models these using computer systems
- - the aim is to create intelligent machines which can function/react like humans by learning and apapting
- Turing Test
- - a test to discover whether a machine's reponse is distinguishable from a human response
- - the test involves a player, a human and a machine.
- - the player does not know which is the human and whish is the machine
- - the player asks questions of the human and the machine nad tries to discover which is the human.
- - the player does not know which is the human and whish is the machine
- Neural Network
- - a neural network models the human brain
- - it consists of a collection of nodes linked by one-way/two-way connections
- - each node calculates the weighted sum of it's inputs and provides an output
- - Backward propagation may be used
- - each node calculates the weighted sum of it's inputs and provides an output
- - it consists of a collection of nodes linked by one-way/two-way connections
- - a neural network models the human brain
- Expert Systems
- - an application of AI to a particular area of activity where traditional human expert knowledge and experience are made available through a computer package
- - knowledge rich, subject often represented as "facts and rules" in the expert system.
- - once a knowledge base has been constructed, an expert system is ready to be interrogated.
- - the system requests the user to provide information and then searches the knowledge base to find appropriate advice for the user.
- - knowledge base is updated when new information becomes available on the results of it's use
- Examples
- - life insurance consults:
- - car insurance:
- - life insurance consults:
- - the system requests the user to provide information and then searches the knowledge base to find appropriate advice for the user.
- - once a knowledge base has been constructed, an expert system is ready to be interrogated.
- - knowledge rich, subject often represented as "facts and rules" in the expert system.
- - an application of AI to a particular area of activity where traditional human expert knowledge and experience are made available through a computer package
- Knowledge Base
- - part of an expert system that holds knowledge about the application area (or domain)
- - knowledge base is updated when new information becomes available on the results of it's use
- - often much of the knowledge is held as IF...THEN...type rules and this knowledge is called a rule base
- Knowledge Engineer
- - obtains knowledge required for the expert system
- - using structured/ unstructured interviews/ problem solving/ concept maps
- - structures the knowledge into a database
- - validates/ verifies the knowledge
- - structures the knowledge into a database
- - using structured/ unstructured interviews/ problem solving/ concept maps
- - obtains knowledge required for the expert system
- - part of an expert system that holds knowledge about the application area (or domain)
- Inference Engine
- - a peice of software in an expert system that interrogates the knowledge as a result draws inferences or conclusions
- Shell
- - a piece of software that is an "empty" expert system without the knowledge base for any particular application.
- - the user enters the appropriate rules and facts
- - the software development environment for creating an expert system
- - contains components of an expert system
- - can be populated for the particular application.
- - knowledge acquisition system/ knowledge base /inference engine /user interface
- - can be populated for the particular application.
- Heuristics
- - rules that aren't derived purely from logic but are derived from self experience
- - "rules of thumb"
- - many rules in an expert system are of this type.
- Fuzzy Logic
- - a means of working with uncertain knowledge
- - whereas in classical logic we treat statements as being either true or false, in fuzzy logic we give each of these possibilities a certainty between 0 and 1
- - a means of working with uncertain knowledge
- - rules that aren't derived purely from logic but are derived from self experience
- - Considers all aspects of intelligence and models these using computer systems
Similar ICT resources:
Teacher recommended
Comments
No comments have yet been made