Scribd
Upload
54 views34 pages

Chapter 1 - Intro To AI

Uploaded by

somsonengda
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
54 views34 pages

Chapter 1 - Intro To AI

Uploaded by

somsonengda
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 34

1

Wollo University ,Kombolicha Institute of Technology

Department of Software Engineering

Fundamental of Artificial Intelligence

By Ashenafi Workie(MSc.)
KIOT@SE by Ashenafi Workie
Major chapters outlines

1 Chapter 1: Introduction to Artificial intelligence


2 Chapter 2: Intelligent Agent
3 Chapter 3: Solving Problems
4 Chapter 4: Knowledge and Reasoning
5 Chapter 5: Uncertain Knowledge and Reasoning
6 Chapter 6: Learning
7 Chapter 7:Communicating, Perceiving, and Acting 3
Assessment Methods

• Assignments and Lab [20%]


• Mid and Quiz [30%]
• Project and presentation [10%]
• Final Exam [50%]

4
What is Artificial Intelligence

5
What is Artificial Intelligence

6
Cont’d

 Artificial Intelligence (AI)is machine-displayed intelligence that simulates human


behavior or thinking and can be trained to solve specific problems.
 It is the part of computer science concerned with designing intelligent computer systems,
that associate with intelligence in human behavior
 understanding language,
 learning,
 reasoning,
 solving problems, and so on.

7
Intelligence
• Defined in a human context: able to
• Reason in an abstract manner
• Mental representation (purpose
based?)
• Problem solving
• Learning
• emotional knowledge
• creativity
• Most of all it is adaptation to meet
the demands of the environment
effectively
8
Intelligence behavior

9
Intelligence behavior
• Reasoning: make inferences given a set of premises/based on the
current situation
• Inductive vs Deductive inferences/reasoning
• Problem-Solving: Given data find a solution to a problem
• Special purpose solution: customized solution to a specific
problem
• General purpose solution: solution to several problems

10
Intelligence behavior

11
Intelligence behavior
• Perception: scan the environment using different sensors – Camera, Ultrasonic sensors,
LiDAR, etc.
• Internally the scanned information is interpreted to understand the background
• Language Understanding: speech, written statements, signs, and symbols
• Learning: trial and error based learning, memorizing solutions to different problems,
vocabulary, etc.
• Use these later for different task

12
Approach to AI
• Several approaches exist to study AI:
• Human Centric approach: which derives
much from humans
• Human thinking – internal
• Human Action – external

• Dissociate from humans and focus on doing


the 'right thing’ – (perfection – because
humans are limited)
• Rational thinking - process
• Rational action – behavior
• Important because there are numerous
contexts where mimicking human
thought/action is not important
13
Human center approach to AI
• Thinking like Humans:
• Is a cognitive (?) modelling approach to AI
• Requires understanding of the internal activities of
the brain via
• Introspection – observing ourselves
• Brain imaging — observing the brain in action
• Psychological experiments (E.g. Rorschach
Test, )
• Formulate a precise theory of the mind, it becomes
possible to express the theory as a computer
program.
• Goal is to make program’s input-output behavior
match human behavior (After testing)

https://openpsychometrics.org/tests/HEMCR/

14
Human center approach to AI
• Acting Like Humans (Blackbox):
• A.K.A the Turing Test Approach
• Turing test: Assume there’s a person asking questions
blindly (person/machine)
• If the person cannot distinguish the machine’s
answer from the person’s the machine has passed
the test
• Pragmatic/realistic/practical approach to answer
the question of whether machines think or not
• The machine should have the following:
• Natural language processing
• Knowledge representation
• Automated reasoning
• Machine learning
• Computer Vision (Total Turing test)
• Robotics (Total Turing Test)
15
Rationalistic approach to AI
• Rationalistic Thinking:
• The “laws of thought” (Logic) approach
• Aristotle attempted to codify an
irrefutable reasoning process.
• His syllogisms provided patterns
for argument structures that
always yielded correct conclusions
when given the correct premises
• The Logic approach assumes a certain
deterministic world – does not incorporate
uncertainty (stochastic nature)

• The theory of probability fills this gap,


allowing rigorous reasoning with uncertain
information 16
Rationalistic approach to AI
• Rationalistic Action (for systems that operate
and act autonomously):
• A.K.A. the Rational Agent Approach
• An agent is just something that acts (agent comes
from the Latin agere, to do)
• A rational agent is one that acts so as to achieve
the best outcome or,
• Best outcome is defined by the objective given to
the agent (Utility based)
• Rationality in some context’s may not be limited to
making inferences as in Logic
• E.g. recoiling from a hot stove is a
reflex action
• Another illustration is learning not only for
erudition but also because it improves our ability
to generate effective behavior, especially in
circumstances that are new (improvise) 17
Example Apps in AI

18
Level of Artificial Intelligence

19
Level of Artificial Intelligence

20
Level of Artificial Intelligence

21
AI Vs ML Vs DL

22
AI Vs Data science

23
AI levels and categories

24
AI levels and categories

25
Different AI categories

26
Machine learning

27
Goals of Artificial Intelligence

28
Goals of Artificial Intelligence

29
Application area

• Automating both mundane and expert tasks


• Paradoxically, it turns out that it is the mundane tasks that are generally much the hardest
to automate
• Mundane Tasks (Image and Pattern Recognition)
• Robots in Assembly plants etc.
• Natural Language Processing (understanding, generation, translation)
• Formal Tasks (Games, Puzzles, Mathematics)
• Expert Tasks (Medical Diagnosis, Fault finding, Engineering)

30
Application area

31
Application area

32
Application area

33
End ….

34

You might also like