artificial intelligence priti sajja spuniversity
Post on 20-Oct-2014
1.455 views
DESCRIPTION
TRANSCRIPT
Artificial Intelligence
Priti Srinivas Sajja Associate Professor
Department of Computer Science Sardar Patel University
Visit priti sajja.info for detail
1 Created By Priti Srinivas Sajja
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
2 Created By Priti Srinivas Sajja
Natural intelligence
Responds to situations flexibly.
Makes sense of ambiguous or erroneous messages.
Assigns relative importance to elements of a
situation.
Finds similarities even though the situations might
be different.
Draws distinctions between situations even though
there may be many similarities between them.
Introduction
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
3 Created By Priti Srinivas Sajja
Artificial intelligence
Introduction
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
4 Created By Priti Srinivas Sajja
Artificial intelligence
Introduction
where people are better
human thought process
characteristics we associate with intelligence
knowledge using symbols
heuristic methods
non-algorithmic
Constituents of artificial intelligence
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
5 Created By Priti Srinivas Sajja
Artificial intelligence
Introduction
Extreme
solution, either
best or worst
taking
(infinite) time
time
Acceptable
solution in
acceptable
time
Nature of AI solutions
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
6 Created By Priti Srinivas Sajja
Testing Intelligence
AI Tests
Turing test will fail to test for intelligence in two circumstances;
1. A machine may well be
intelligent without being able to chat exactly like a human; and;
2. The test fails to capture the general properties of intelligence, such as the ability to solve difficult problems or come up with
original insights. If a
machine can solve a difficult problem that no person could solve, it would, in principle, fail the test.
Can you tell
me what is
222222*67344
?
Why
Sir?
The Boss could not judge who was replying, thus the machine is as intelligent as the secretary.
The Turing test
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
7 Created By Priti Srinivas Sajja
Can you find any test to check the given system is intelligent or not?
AI Tests
If it talks like human
Translates, summarizes, and learns
Solves your problem
Reacts differently
Walks, perceives, tests,
smells, and feels like human
conceptually form a test
and use it in different situation
before accepting it.
Makes and understands joke
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
8 Created By Priti Srinivas Sajja
Rich & Knight (1991) classified and described the different areas that Artificial Intelligence techniques have been applied to as follows:
Applications Mundane Tasks
• Perception - vision and
speech
• Natural language
understanding, generation,
and translation
• Commonsense reasoning
• Robot control Formal Tasks
• Games - chess,
backgammon, checkers, etc.
• Mathematics- geometry,
logic, integral calculus,
theorem proving, etc.
Expert Tasks
• Engineering - design, fault
finding, manufacturing
planning, etc.
• Scientific analysis
• Medical diagnosis
• Financial analysis
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
9 Created By Priti Srinivas Sajja
Basic transactions by operational
staff using data processing
Middle management uses reports/info.
generated though analysis and acts
accordingly
Higher management generates
knowledge by synthesizing
information
Strategy makers apply morals,
principles, and experience to generate
policies
Wisdom (experience)
Knowledge (synthesis)
Information (analysis)
Data (processing of raw observations )
Volume Sophistication
and complexity
TPS
DSS, MIS
KBS
WBS
IS
Data pyramid
Data Pyramid
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
10 Created By Priti Srinivas Sajja
According to the classifications by Tuthhill & Levy (1991), five main types
of KBS exists:
Expert systems
Linked Systems
CASE based Systems
Intelligent Tutoring Systems
Intelligent User Interface for Database
Knowledge base
Inference engine
User interface
Explanation and
reasoning
Self- learning
General structure of KBS Knowledge Based systems
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction Knowledge Sources and Types
11 Created By Priti Srinivas Sajja
Knowledge Based systems
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction Knowledge Representation
12 Created By Priti Srinivas Sajja
Knowledge Based systems
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction Intelligence, explanation and reasoning
Partial self learning, uncertainty handling
Documentation of knowledge
Proactive problem solving
Cost effectiveness
Nature of knowledge
Large volume of knowledge
Knowledge acquisition techniques
Little support to engineer AI based systems
Shelf life of knowledge and system
Development Effort
13 Created By Priti Srinivas Sajja
Pros and Cons
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction Bio-Inspired Computing New approaches to AI
Taking inspiration form nature and biological systems
Includes models such as Artificial Neural Network (ANN),
Genetic Algorithm(GA),
Swarm Intelligence(SI), etc.
Nature has virtues of self learning, evolution, emergence and immunity
The objective of bio-inspired models and techniques to take inspiration from Mother Nature and solve problems in more effective and intelligent way
14 Created By Priti Srinivas Sajja
Bio-inspired
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction Artificial Neural Network (ANN) An artificial neural network (ANN) is connectionist model of
programming using computers.
An ANN attempts to give computers humanlike abilities by mimicking the human brain’s functionality.
The human brain consists of a network of more than a hundred billions interconnected neurons working in a parallel fashion.
15 Created By Priti Srinivas Sajja
Bio-inspired
A biological neuron An artificial neuron
X2
X1
XiWi
W1
W2
… ….
y
Xn
W
n
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
16 Created By Priti Srinivas Sajja
Bio-inspired
W12 X1
X2
X3
.
.
.
.
Xn
O0
O1
….
Om
.
.
.
.
.
.
.
.
.
.
.
.
W1h
Input layer Hidden layers
Output layer
A multilayer perceptron
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction Genetic Algorithms (GA) • It mimics Nature’s evolutionary approach • The algorithm is based on the process of natural selection—
Charles Darwin’s “survival of the fittest.” • GAs can be used in problem solving, function optimizing,
machine learning, and in innovative systems.
17 Created By Priti Srinivas Sajja
Genetic cycle
Modify with operations
Start with initial population by randomly selected Individuals
Evaluate fitness of new individuals
Update population with better individuals and repeat
Initial population
Selection Mutation Crossover
Evaluating new individuals through fitness function
Modify the population
Bio-inspired
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
Swarm Intelligence Inspired by the collective behavior of social insect
colonies and other animal societies
Ant colony, fish school, bird flocking and honey comb are the examples
18 Created By Priti Srinivas Sajja
Bio-inspired
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction Some more examples ….
19 Created By Priti Srinivas Sajja
Bio-inspired
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
20 Created By Priti Srinivas Sajja
Fu
zzy In
terface
Structure of proposed system
Fuzzy interface
Linguistic
fuzzy
interface
Fuzzy rule base
and membership
functions
Rulebase
Crisp
Normalized
values
Decision
support
Users choice
and needs
Decision
support
Underlying
ANN P1
P
2 P3
P4
Implicit and
self learning
by ANN
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
21 Created By Priti Srinivas Sajja
Example
Artificial Intelligence
AI Tests
Applications
Data Pyramid
Knowledge Based Systems
Pros and Cons
Bio-inspired
Example
Acknowledgement
Introduction
22 Created By Priti Srinivas Sajja
References llustrationsOf.com
www.gadgetcage.com
Engadget.com
scenicreflections.com
lih.univ-lehavre.fr
business2press.com
globalswarminghoneybees.blogspot.com
Knowledge-based systems, Akerkar RA and Priti Srinivas Sajja, Jones & Bartlett Publishers, Sudbury, MA, USA (2009)