Lecture 01b
Lecture 01b
Lecture 01b
Artificial
Intelligence “Understanding of
Human
Mind”
“Augmentation •Cognitive science,
of Human Abilities” developmental psychology,
linguistic, philosophy.
•Engineering, mathematics,
economics, computer science,
operational research.
Augmenting Human Abilities
INFANOID: to understand
infant-adult interaction
Symbolical processing
Solve problem by symbolic representation, rather
than number
Heuristics
Short-cut, rules of thumb, reduce the problem scope
Making conclusion & inference
Explaining, from experience (data..data..data)
Non-Algorithmic
Procedures are quite robust, not tied to the step by
step
AI as different approach in
computing world
“AI and Our Intelligence”
Based on well defined problem and Steps by steps solution and not that
representation ~ dynamic! robust enough
Now Onwards~
AI Application
AI ‘big’ family
The Philosophical Foundations of Artificial Intelligence
Applications using Artificial Intelligence
MS Word + office
assistant
Searching function in
search engine
Office assistant
Intelligent washing
machine
Game
Junk mail filtering
Branches of AI
Machine Learning
Speech Understanding
Automatic
Programming Robotic
Natural Language Game Playing
Processing
Neural Network
Expert System
Fuzzy Logic
Intelligent Tutor AI Genetic Algorithm
Computer Vision Tree
Machine
Huge Data from Information/
Learning
database knowledge
algorithm
Computer Vision
concerned with the theory for building
artificial systems that obtain information
from images and apply to the computer
system
The image data can take many forms, such
as a video sequence, views from multiple
cameras, or multi-dimensional data from a
medical scanner.
Applications of computer vision systems include systems for:
Controlling processes (e.g. an industrial robot or an autonomous vehicle).
Detecting events (e.g. for visual surveillance or people counting).
Organizing information (e.g. for indexing databases of images and image
sequences).
Modeling objects or environments (e.g. industrial inspection, medical image
analysis or topographical modeling).
Interaction (e.g. as the input to a device for computer-human interaction).
Fuzzy Logic
Fuzzy : Blurred, Fluffy, Frayed or Indistinct
To overcome ‘world’ problem which are covered by uncertenties
Today temperature is 40 C
Today is really hot
Based on fuzzy set : degree to which events occur rather than the
likelihood of their occurrence (probability)
Application
Air conditioners
Cameras
Digital image processing,
(such as edge detection)
Rice cookers
Dishwashers
Elevators
Washing machines
other home appliances
Video game artificial intelligence
More..
Intelligent tutoring system (ITS), broadly defined, is any computer system that
provides direct customized instruction or feedback to students, i.e. without the
intervention of human beings
Genetic algorithm (GA) is a search technique used in computing to find exact or
approximate solutions to optimization and search problems.. Idea comes from human
chromosomes or the genotype or the genome
Natural language processing (NLP) is a subfield of artificial intelligence and computational
linguistics. It studies the problems of automated generation and understanding of natural human
languages.
Philosophical Foundations
of
Artificial Intelligence
Philosophical Questions in AI
How can mind arise from nonmind? (This is the
mind-body problem.)
50
Human Vision (2)
51
Human Vision (3)
52
Relax
Test:How many human faces in the
picture?