Please enable JavaScript.
Coggle requires JavaScript to display documents.
UNIT 5 : ARTIFICIAL INTELLIGENCE (Alan Turning (Turing Machine…
UNIT 5 : ARTIFICIAL INTELLIGENCE
Definition: Machines that perform tasks that seem to require intelligence when performed by human
Russel & Norvig (1995)
Think like humans
Closely related to field of cognitive science
Actual workings of human mind & implement on computer
Approach is by psychological experiment, the other by introspection
Biologically to reconstruct a computer brain in the same manner as human brain
Act like humans
Do what human do
Regardless of whether it is done the same way as humans
If machine can do what human do, then it is INTELLIGENCE
Think rationally
Study of mental faculties through the use of computational models
The study of the computations that make it possible to perceive, reason & act
Act rationally
An agent is something that acts
Perceives its environment through sensor
Act upon the environment through effectors
To distinguish an agent from any other program
To perceive its environtment
Adapt to chance
Operate autonomously
Rational Agent
Acts to achieve the best outcome
Best expected outcome when there is uncertainly
Alan Turning
Concept of algorithm to digital computers
Relationship between machines & nature created the field of artificial intelligence
Code cracker (cryptanalyst)
Decipher German coded signals
Wartime German computer ENIGMA generated constantly changing code
Turing Machine
Theoretical computer
Very simple but powerful device
Based on idea : Human intelligence is the ability to solve problems
Also known as "universal machine"
Turing Test
Machines could be created that would mimic the processes of the human brain
Intelligence behavior as the ability to achieve human-level performance on all cognitive tasks , sufficient to fool an interrogator
Able to process human language
Store information given prior to the test
Be able to learn
Able to perceive objects (computer vision)
Able to move objects (robotics)
John Von Neumann
Mathematician
Developed ENIAC (18000 vacuum tubes)
Make use of punch cards
Huge & took up a lot of space
Use to calculate artillery tables that make it possible to aim artillery at specific target
EDVAC
Smaller than ENIAC (5000 vacuum tubes)
Instruction for operations & date could be stored in the computer's memory
Central Processing Unit (CPU)
Artificial Intelligence: The Machine Performs
Early Programs
General problem solver
Computer program that approach problem solving the way humans do
General Problem Solver (GPS)
Able to solve variety of problems
To solve problems were seen to comprise:
Problem space (Where the task occur)
Initial state (The beginning condition)
Expert Systems
The reliance on knowledge of a human domain expert for system's problem-solving strategies
Example of human domain expert:
Doctor
Chemist
Geologist
Engineer
AI researchers what is known as knowledge-based systems
Great number of information within a narrow field
Example of filed
Medecine
Chemistry
Biology
Chess
Forensic anthropology
Machine (Mechanic)
Component of expert system
Knowledge base
Engine (Inference mechanism)