Werabe University

Institute of Technology
Department of IT
Course: Artificial Intelligence

Chapter One
Introduction to AI
 Intelligence
• Intelligence is the capability of observing, learning, remem-
bering & reasoning.
• AI attempts to develop intelligent agents.

Characteristics of Intelligent system

 Use vast amount of knowledge
 Learn from experience and adopt to changing environment
 Interact with human using language and speech
 Respond in real time
 Tolerate error and ambiguity in communication
 Human Intelligence
How do people Reason?
 They create categories & relate one concept to another: Reasoning by analogy:

From the fact that: A is like B. M is in A. N is in B. Can we say “M is like N”?

 They use specific rules: rule-based reasoning

– if ‘a’ then ’b’
if ‘b’ then ‘c’
abc
 Use Past Experience, “CASES” (case-based reasoning)
– Similarities of current and previous case
– Store cases using key attributes
 Use “Expectations” (probabilistic reasoning)
– With the help of previous experience, they guess the probability of occurrence of
events or guess solution for the problem at hand.
 Deductive and inductive reasoning
 Deductive reasoning: reasoning from general
premises, which are known or presumed to be
known, to more specific, certain conclusions.
– Gravity makes things fall. Hence, the apple that hit my
head was due to gravity.
–All athletes work out in the gymnasium. Henok is an athlete. Therefore,
Henok works out in the gymnasium.
•Inductive reasoning: reasoning from a set of specific facts or individ-
ual cases to a more general, but uncertain, conclusions.
– The first five apples I picked from this tree are sweet, my friend also men-
tioned the apples from this tree are sweet. Therefore, All apples from this
tree are sweet.
 Examples
 A classic example of deductive reasoning, given by Aristotle:
– All men are mortal. (major premise)
– Socrates is a man. (minor premise)
– Socrates is mortal. (conclusion)

 The wheel is round. (Or, all wheels I have seen are round)
–using inductive reasoning we can infer the general proposition: All wheels
are round.
 The bird flies. (Or, all birds I have seen could fly)
–using inductive reasoning we can infer the general proposition: All birds
can fly.
 Artificial Intelligence
• The concern of AI is to develop computer-based system that be-
have like human and emulate the reasoning power of humans
• In order to do tasks that require human intelligence.
– Which task requires intelligence?
• Complex arithmetic operations
– For instance, Solving 220 * 350?
• Mundane tasks: all tasks routinely done by all of us in our day-to-day
activities:
– Example, Natural language understanding; face recognition
• Expert tasks: which require specialists' knowledge
– Example, Medical diagnosis; computer maintenance; financial plan-
ning
 Views of AI
 AI is found on the premise that:
– workings of human mind can be explained in terms of computation,
and
– computers can do the right thing given correct premises and reasoning
rules.

Views of AI fall into four categories:

Thinking humanly Thinking rationally

Acting humanly Acting rationally
 Thinking humanly: The Cognitive Modeling

 Reasons like humans do

– Programs that behave like humans
 Requires understanding of the internal activities of the brain
– see how humans behave in certain situations and see if you
could make computers behave in that same way.
Example. write a program that plays chess.
– Instead of making the best possible chess-playing program,
you would make one that play chess like people do.
 Acting humanly: The Turing Test
Can machines act like human do? Can machines behave intelli-
gently?
 Turing Test: Operational test for intelligent behavior
– Do experiments on the ability to achieve human-level performance,
– Acting like humans requires AI programs to interact with people
 Suggested major components of AI: knowledge, reasoning, lan-
guage understanding, learning
 Thinking Rationally: The Laws of Thought
 A system is rational if it thinks/does the right thing through cor-
rect reasoning.

 Aristotle: provided the correct arguments/ thought structures

that always gave correct conclusions given correct premises.
– Abebe is a man; all men are mortal; therefore, Abebe is mortal
 Acting rationally: The rational agent

 Doing the right thing so as to achieve one’s goal, given one’s

beliefs.
 AI is the study and construction of rational agents (an agent that
perceives and acts)
 Rational action requires the ability to represent knowledge and
reason with it so as to reach good decision.
– Learning for better understanding of how the world works
 Applications of AI
Solving problems that required thinking by humans:
 Playing games (chess, checker, cards, ...)
– Great advances: the AI software Deep Blue beats human expert Kas-
parov.
 Classification of text (Politics, Economic, Social, Sports, etc.)
 Information filtering and summarization of text
 Writing story and poems; solving puzzles
 Giving advice in Medical diagnosis, Equipment repair, Computer
configuration, Financial planning, …
 How to make computers act like humans?
The following sub-fields are emerged
 Natural Language processing (enable computers communicate in human
language, English, Amharic, ..)
 Knowledge representation (schemes to store information, both facts and
inferences, before and during interrogation)
 Automated reasoning (use stored information to answer questions and to
draw new conclusions)
 Machine learning (adapt to new circumstances and accumulate knowl-
edge)
 Computer vision (recognize objects based on patterns in the same way
as the human visual system does)
 Robotics (produce mechanical device capable of controlled motion with the
ability to move, see, hear, and accordingly take actions in the world, possibly
responding to new perceptions)
 AI vs HI?
 Artificial Intelligence (or AI) is the field that explores to develop
a system that think in the same sense as humans do.
 Remember computer-based chess program (Deep Blue) that beats human
expert (Gary Kasparov). What do you understand from this?
 Is AI equals human intelligence?
– Is that possible to create a computer system called mind?
 What is our concern in designing an Intelligent agent?
– Is that to replace human beings or to support and give leverage to them
such that they can engage themselves in expert works?
 Strong AI vs Weak AI
 Strong AI argues that it is possible that one day a computer will be in-
vented which can be called a mind in its fullest sense.
– Strong AI aims to create an agent that can replicate humans' intelligence
completely; i.e., it can think, reason, imagine, etc., & do all the things that
are currently associated with the human brain.
 Weak AI, on the other hand, argue that computers can only appear to
think & are not actually conscious in the same way as human brains are.
– The weak AI position holds that AI should try to develop systems which
have facets of intelligence, but the objective is not to build a completely
sentient/conscious entity.
– Weak AI researchers see their contribution as systems like expert systems
used for medical diagnosis, which use "intelligent" models, but they do not
help create a conscious agent
 History of AI
 Formally initiated in 1956 and the name AI was coined by John
McCarthy.
 The advent of general-purpose computers provided a vehicle for
creating artificially intelligent entities.
–Used for solving general-purpose problems

 Which one is preferred?

–General-purpose problem-solving systems
–Domain specific systems
 History of AI…
 Development of knowledge-based systems: the key to power
– Performance of general-purpose problem-solving methods is weak for
many complex domains.
– Use knowledge more suited to make better reasoning in narrow areas
of expertise (like human experts do).
Knowledge base systems (KBSs)
 Deal with treating knowledge and ideas on a computer.
– Emphases to the importance of knowledge.
 Use inference to solve problems on a computer.
– Knowledge-based systems describes programs that reason over exten-
sive knowledge bases.
 Have the ability to learn ideas so that they can obtain informa-
tion from outside to use it appropriately.
– The value of the system lies in its ability to make the workings of the
human mind understandable and executable on a computer.
 History of AI…
 Shifts from procedural to declarative programming paradigm.
– Rather than telling the computer how to compute a solution, a program
consists of a knowledge base of facts and relationships.
– Rather than running a program to obtain a solution, the user asks ques-
tion so that the system searches through the KB to determine the an-
swer.
 Simulate human mind and learning behavior (Neural Network,
Support Vector Machine, Hidden Markov Models, etc. )
 Programming paradigms
 Each programming paradigms consists of two aspects:
– Methods for organizing data/knowledge,
– Methods for controlling the flow of computation

 Traditional paradigms:
Programs = data structure + control

 AI programming paradigms:
Programs = knowledge structure + inference
 Sub-fields of Artificial Intelligence
 AI now consists many sub-fields, using a variety of techniques, such as:
– Neural Networks – e.g. brain modeling, classification
– Computer Vision – e.g. object recognition, image understanding
– Natural Language Processing – e.g. machine translation
– Robotics – e.g. intelligent control, autonomous exploration
– Expert Systems – e.g. decision support systems, teaching systems
– Evolutionary Computation – e.g. genetic algorithms, genetic programming
– Speech Processing– e.g. speech recognition and production
– Planning – e.g. scheduling, game playing
– Machine Learning – e.g. decision tree learning