You are on page 1of 26

‫بسم هللا الرحمن الرحيم‬

King Abdulaziz University


Faculty of Computing and information Technology
Computer Science Department

CPCS-335 Introduction to Artificial Intelligence

Introduction (cont.)

Imtiaz Hussain Khan, PhD Abdullah Basuhail, PhD


ihkhan@kau.edu.sa abasuhail@kau.edu.sa
CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G
1
Recap
 AI is the science and engineering of making intelligent machines
 AI is a multidisciplinary field wherein computer science glues together
the different disciplines, including mathematics, linguistics etc.
 Turing test is a commonly used intelligence test
 Four main approaches to AI: Thinking vs. Acting

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


2
Today’s Plan
 AI Branches
 AI Applications
 Brief History of AI

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


3
Branches of AI
 Logical AI
 Search
 Pattern recognition
 Knowledge representation
 Common sense knowledge and reasoning
 Learning
 Planning
 Heuristics
 Genetic programming
 (...) CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G
4
Logical AI
 Logic is language of reasoning
 Amongst other things, logic provides a formal way to express syntax and
semantics of languages
 Different types of logic exist
• Propositional logic
• Predicate logic
• Fuzzy logic
• Temporal logic
 Propositional and predicate logic are fundamentals to all logics – will be
reviewed in this course
CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G
5
Search in AI
 Search is a problem-solving technique which systematically considers
different possible actions to find path from a start state to a final state
 Search techniques are broadly divided into
• Uninformed search (unintelligent search)
• Informed search (intelligent search)
 Example search problems
• Travelling salesman problem
• N-queens problem

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


6
Pattern Recognition
 Identifying recurring patterns in input data with the goal of
understanding or categorizing that input
 Example pattern recognition problems
• Face recognition
• Hand-writing recognition
• Speech recognition
 Pattern recognition approaches
• Template matching
• Statistical matching/classification
• Structural matching
CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G
7
Knowledge Representation (KR)
 Knowledge is a collection of facts about the world
 To manipulate these facts by a program, they need to be represented in
a suitable manner
 Different KR formalisms exists
• Logic as KR tool, e.g. Predicate logic
• Semantic networks
• Production rules
• Frames

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


8
Common Sense Knowledge
 Common sense is the mental skill or ability to analyze situations based
on a given context
• People can think, but computers can’t
 Common sense capabilities are generally divided into
• Common sense knowledge
• Common sense reasoning
 OpenMind project at MIT aims to develop common sense in computers
by teaching them
• Frames

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


9
Learning
 Learning is making useful changes in the working of our mind (Marvin
Minsky, 1986)
• People can learn from their environment
 Major paradigms of machine learning
• Supervised learning
• Unsupervised learning
• Reinforcement learning
• Deep learning – a relatively new area

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


10
Applications of AI
 Game playing (e.g. chess)
 Natural language processing (e.g. understanding text)
 Speech recognition (e.g. answering machines)
 Computer vision (e.g. face recognition)
 Expert systems (e.g. medical diagnosis)
 (...)

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


11
Brief History of AI
 1943: early beginnings
• McCulloch & Pitts: Boolean circuit model of brain
 1950: Turing
• Turing's Computing Machinery and Intelligence
 1956: Name coined
• Dartmouth meeting: Artificial Intelligence by McCarthy et al
 1956 - 65: Great enthusiasm
• Newell and Simon: GPS (General Problem Solver)
• Gelertner: Geometry Theorem Prover
• McCarthy: invention of LISP (List Processing, a functional language)
CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G
12
Brief History of AI (cont.)
 1966-73: Towards reality
• Realization that many AI problems are intractable
• Limitations of existing neural network methods identified
• Neural network research almost disappears

 1969-85: Adding domain knowledge


• Development of knowledge-based and rule-based systems
• DENDRAL, MYCIN

 1986-- Rise of machine learning


• Neural networks return to popularity
• Major advances in machine learning algorithms and applications
CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G
13
Brief History of AI (cont.)
 1990 -- Role of uncertainty
• Bayesian networks as a knowledge representation framework
 1995-- AI as Science
• Integration of learning, reasoning, knowledge representation
• AI methods used in vision, language, data mining, etc.
 2000-- AI is everywhere

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


14
What we can do with AI at present?
 Play a decent game of Jeopardy? Yes
 Win against any human at chess? Yes
 Win against the best humans at Go? Yes
 Play a decent game of tennis? Yes
 Grab a particular cup and put it on a shelf? Yes
 Drive safely along the highway? ?
 Buy a week's worth of groceries on the web? Yes

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


15
What we can do with AI at present?
 Prove a new mathematical theorem? Yes
 Perform a surgical operation? No
 Translate Arabic into English in real time? Yes
 Write an intentionally funny story? No

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


16
Summary
 AI is science and engineering to build intelligent machines
 Strong AI aims to replicate all human capabilities in machines, while
weak AI aims to implement partial human capabilities in machines
 Engineering-based AI aims to build intelligent systems, while science-
based AI aims to understand intelligent behaviour
 Main AI approaches can be classified as Cognitive science-based
approach, Laws of thought-based approach, Turing test-based approach
and Rational agent-based approach

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


17
Summary
 The main branches of AI include: Logical AI, Search and optimization,
Pattern recognition, Knowledge representation, Common sense
knowledge and reasoning, Heuristics and Evolutionary Computation
 The main application areas of AI include: Game playing, Natural
language processing, Speech recognition, Machine vision, Robotics and
Expert Systems

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G


18
Self Review Questions

1 Which of the following is a major paradigm of machine learning?

A Supervised learning 

B Unsupervised learning 

C Reinforcement learning 

D All of the above 

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G Designed by Dr. Abullah Basuhail, KAU, 1441H/2020G
19
Self Review Questions

2 Which of the following is an application of AI?

A Speech recognition 

B Expert systems 

C Machine vision 

D All of the above 

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G Designed by Dr. Abullah Basuhail, KAU, 1441H/2020G
20
Self Review Questions

3 Which of the following logics can model quantities which span over a continuum?

A Propositional logic 

B Predicate logic 

C Temporal logic 

D Fuzzy logic 

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G Designed by Dr. Abullah Basuhail, KAU, 1441H/2020G
21
Self Review Questions

4 Which of the following logics can model quantities which involve time?

A Propositional logic 

B Predicate logic 

C Temporal logic 

D Fuzzy logic 

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G Designed by Dr. Abullah Basuhail, KAU, 1441H/2020G
22
Self Review Questions

5 Who coined the term artificial intelligence?

A Alun Turing 

B John McCarthy 

C Elrich 

D All of the above 

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G Designed by Dr. Abullah Basuhail, KAU, 1441H/2020G
23
Self Review Questions

6 Which year the term artificial intelligence was coined?

A 1943 

B 1950 

C 1956 

D 1960 

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G Designed by Dr. Abullah Basuhail, KAU, 1441H/2020G
24
Self Review Questions

7 Which period witnessed a decline in AI research?

A 1960-65 

B 1970-80 

C 1966-73 

D 1990-2000 

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G Designed by Dr. Abullah Basuhail, KAU, 1441H/2020G
25
Self Review Questions

8 Which year the AI regained popularity?

A 1956 

B 1960 

C 1986 

D 2000 

CPCS335, Introduction to Artificial Intelligence, CS, FCIT, KAU, 1441H/2020G Designed by Dr. Abullah Basuhail, KAU, 1441H/2020G
26

You might also like