Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
18 Cards in this Set
- Front
- Back
Agent Diagram |
|
|
Stimuli |
Stimuli - Light, sounds, words typed, mouse movements, information from databases and web pages, physical bumpsComes from sensors |
|
Percepts |
Perceive the environment through the body More specialized: Lines, edges and depth information, hand signals given by a human |
|
Controller |
The Brain Sends commands based on the percepts |
|
Command |
Low level commands: set the voltage of a motorHigh-level commands: stop, enter room 103 |
|
Actuator |
What convert commands into actions Noisy in the case of robots |
|
What makes up an agent? |
Perception + Reasoning + Action |
|
What is a world? |
Agent + Enviornmnet |
|
Interacting with enviornment |
Prior knowledge about the agent and the environment History of interaction with the environment, which is composed of: -Observations of the current environment -Past experiences of previous actions and observations, or other data, from which it can learn Goals that it must try to achieve or preferences over states of the world Abilities: the primitive actions it is capable of carrying out. |
|
What is utility |
Utility is a term used by economists to describe the measurement of "useful-ness" that a consumer obtains from any good Satisfaction |
|
Knowledge representations |
Insert image |
|
What is knowledge and Knowledge base |
Information about a domain - Used to solve problems of that domain Knowledge base - Representation of all of the knowledge that is stored by an agent |
|
Characteristics of Good KR |
Rich enough As close to problem as possible Amenable to efficient computation Able to aqure from people, data and past experiances |
|
Aproches to Designing a Knowledge representation schemes |
Start with some of the objectives - Then try to expand to incorporate others |
|
Types of Solutions to a Problem |
Optimal (best according to a measure) - Cardinal measures used(utility) Sacrificing -can be accepted according to description Approximately optimal - Close to optimal Probable solution - Often need true-positive and false-positive |
|
Problem representation - Symbols |
Any intelligent agent is necessarily a physical symbol system A physical symbol system is all that is needed for intelligent action |
|
Reasoning |
User doesn't specify how, just what |
|
GOFAI |
Symbolic AI Opposing approach is computational intelligence - nature inspired computational methodologies and address real world specific problem ex- Neural Networks, Evolutionary Computation |