Artificial Intelligence
Lecture-1
Mr. Wasif Akbar
Course Outline
Introduction to Artificial Intelligence (AI) history and applications
Strong AI and weak AI
Knowledge representation
Problem solving in AI using knowledge representation, searching and reasoning
Uniformed and heuristic search
Machine learning
Laws of robotics
Python Programming
Advanced AI topics, Natural language processing, ANN, Fuzzy logic, classification
and clustering algorithms
Learning Outcomes
Understand meaning of AI, its alternative approaches and the implications of AI
for cognitive science more broadly
Expand knowledge about inform and uniform search heuristic search, genetic
algorithms, planning and learning algorithms
Understand the basic methods in planning and reasoning using both logic and
uncertain inference
Know a variety of ways to represent and retrieve knowledge and information
(Expert system, Agents)
Know the fundamentals of AI programming techniques and advanced machine
learning in a modern programming language
Text Book
Stuart Russell and Peter Norvig, Artificial Intelligence. A Modern Approach, 3rd
edition, Prentice Hall, Inc., 2010.
Hart, P.E., Stork, D.G. and Duda, R.O., 2001. Pattern classification. John Willey &
Sons.
Reference Book
Artificial Intelligence: Structures and Strategies for Complex Problem Solving,
George F. Luger, Addison Wesley Publisher.
What is Artificial Intelligence?
- AI is a field of study that encompasses computational techniques for performing
tasks that apparently require intelligence when performed by humans.
- AI is the branch of computer science that is concerned with the automation of
intelligent behaviour.
- AI is concerned with developing computer systems that can store knowledge and
effectively use the knowledge to help solve problems and accomplish tasks.
History of AI
Classical Period (1950-1956)
Game Playing, Theorem proving, State space approach
Romantic Period (1960-1970)
Knowledge representation technique “semantic net”
Modern Period (1970- present)
Expert system, Artificial neurons, Pattern recognition
Components of AI
Hardware Components of AI
Pattern Matching, Problem Solving, Heuristic Search, Natural Language processing,
Knowledge Representation, Expert System, Neural Network, Learning, Planning,
Semantic Network
Software Components
Machine Language, High level Language, LISP Language, Natural Language,
Particular Problem Solving Language
Architectural Components
Uniprocessor, Multiprocessor, Parallel Processor, Distributed Processor
Weak and Strong AI
- The strong AI is very much promising about the fact that the machine is almost
capable of solve a complex problem like an intelligent man.
- The weak AI is not so enthusiastic about the outcomes of AI. Generally weak AI
refers to the use of software to study or accomplish specific problem solving that
do not encompass the full range of human cognitive abilities.
Areas of Artificial Intelligence
- Perception
Machine Vision
Speech Understanding
Touch(tactile or haptic) Sensation
- Robotics
- Planning
- Expert Systems
- Theorem Proving
- Symbolic Mathematics
- Game Playing
Perception
• Machine Vision:
• It is easy to interface a TV camera to a computer and get an image
into memory; the problem is understanding what the image
represents. Vision takes lots of computation; in humans, roughly
10% of all calories consumed are burned in vision computation.
• Speech Understanding:
• Speech understanding is available now. Some systems must be
trained for the individual user and require pauses between words.
Understanding continuous speech with a larger vocabulary is
harder.
• Touch ( tactile or haptic) Sensation:
• Important for robot assembly tasks.
Robotics
• Although industrial robots have been expensive, robot
hardware can be cheap: Radio Shack has sold a
working robot arm and hand for $15. The limiting
factor in application of robotics is not the cost of the
robot hardware itself.
• What is needed is perception and intelligence to tell
the robot what to do; ``blind'' robots are limited to
very well-structured tasks (like spray painting car
bodies).
Planning
• Planning attempts to order actions to achieve goals.
• Planning applications include logistics, manufacturing
scheduling, planning manufacturing steps to construct
a desired product.
• There are huge amounts of money to be saved
through better planning.
Expert Systems
• Expert Systems attempt to capture the knowledge of a
human expert and make it available through a computer
program. There have been many successful and
economically valuable applications of expert systems.
• Benefits:
Reducing skill level needed to operate complex devices.
Diagnostic advice for device repair.
Interpretation of complex data.
“Cloning'' of scarce expertise.
Capturing knowledge of expert who is about to retire.
Combining knowledge of multiple experts.
Intelligent training.
Theorem Proving
• Proving mathematical theorems might seem to be mainly
of academic interest. However, many practical problems
can be cast in terms of theorems. A general theorem prover
can therefore be widely applicable.
• Examples:
• Automatic construction of compiler code generators from a
description of a CPU's instruction set.
• J Moore and colleagues proved correctness of the floating-
point division algorithm on AMD CPU chip.
Symbolic Mathematics
• Symbolic mathematics refers to manipulation of formulas, rather than
arithmetic on numeric values.
Algebra
Differential and Integral Calculus
• Symbolic manipulation is often used in conjunction with ordinary
scientific computation as a generator of programs used to actually do
the calculations. Symbolic manipulation programs are an important
component of scientific and engineering workstations.
Game Playing
• Games are good vehicles for research because they
are well formalized, small, and self-contained. They
are therefore easily programmed.
• Games can be good models of competitive situations,
so principles discovered in game-playing programs
may be applicable to practical problems.
Characteristics of A.I. Programs
• Symbolic Reasoning: reasoning about objects
represented by symbols, and their properties and
relationships, not just numerical calculations.
• Knowledge: General principles are stored in the
program and used for reasoning about novel
situations.
• Search: a ``weak method'' for finding a solution to a
problem when no direct method exists. Problem:
combinatoric explosion of possibilities.
• Flexible Control: Direction of processing can be
changed by changing facts in the environment.
