• Shuffle
    Toggle On
    Toggle Off
  • Alphabetize
    Toggle On
    Toggle Off
  • Front First
    Toggle On
    Toggle Off
  • Both Sides
    Toggle On
    Toggle Off
  • Read
    Toggle On
    Toggle Off
Reading...
Front

Card Range To Study

through

image

Play button

image

Play button

image

Progress

1/15

Click to flip

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;

15 Cards in this Set

  • Front
  • Back

What is AI

AI is the study and design of intelligent agents, where an agent is a system that perceives it's environment and takes an action that maximises it's chance of success

Rational system

A system is rational if it performs the right thing given what it knows.

The four approaches to AI

Thinking Humanly - cognitive science


Acting Humanly - turing test


Thinking Rationally - laws of thoughts , uses math and logic. Not all knowledge can be expressed and it can lead to computational blow up.


Acting Rationally - rational agents

Turing Test

A computer passes the turing test if it can fool the human interrogator.


The interrogator must not the able to differentiate between the answers given by a human and a computer. When they are hidden from sight.


Application of AI

Virtual assistants


Handwriting recognition


Machine translation


Robotics


Autonomous driving


Etc

Turing test problems

The turing test is not reproducible, amenable or constructive to mathematical analysis

What is agent function

It is a function that maps the set of percepts to action.

What is agent program/ architecture

It runs on a physical architecture to produce the agent function

Some fields that contribute to AI

Philosophy - logic


Mathematics - formulation of logic


Economic - rational decision, game theory


Computer engineering - how to build machines that make AI possible.


Etc

Rationality

Measure of how to act to maximize a performance measure

Agent

Is anything that perceives it's environment thru sensors and acts on the environment using actuators.

Is rationality always possible

No

Learning

Agents improve their performance through learning.

Uninformed search

These strategies only use the information available in the problem definition.

Tree search vs graph search

Tree search has no explored nodes list



Graph search has a explored nodes list



So one keeps track the other doesn't.