Scribd
Upload
128 views

Artificial Intelligence: Prof. Dr. Fazlul Hasan Siddiqui

This document provides an introduction to artificial intelligence including: 1) It discusses different approaches to AI such as thinking humanly by modeling human problem solving, acting humanly by passing the Turing test, thinking rationally using logic, and acting rationally to achieve goals. 2) It covers major technologies in AI like machine learning, deep learning, natural language processing, computer vision, planning and scheduling, and solving real-world problems through modeling and reasoning. 3) It provides examples of applying AI to games, medical diagnosis, scene understanding, dialogue processing, and more to highlight capabilities and limitations of different approaches.

Uploaded by

Zain Hamza
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
128 views

Artificial Intelligence: Prof. Dr. Fazlul Hasan Siddiqui

This document provides an introduction to artificial intelligence including: 1) It discusses different approaches to AI such as thinking humanly by modeling human problem solving, acting humanly by passing the Turing test, thinking rationally using logic, and acting rationally to achieve goals. 2) It covers major technologies in AI like machine learning, deep learning, natural language processing, computer vision, planning and scheduling, and solving real-world problems through modeling and reasoning. 3) It provides examples of applying AI to games, medical diagnosis, scene understanding, dialogue processing, and more to highlight capabilities and limitations of different approaches.

Uploaded by

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

Artificial Intelligence

Introduction

Prof. Dr. Fazlul Hasan Siddiqui


Head, Dept. of CSE, DUET, Gazipur
BSc:IUT; MSc:BUET; PhD:ANU (Australia)
[email protected]
Credit: Prof. Joerge Hoffman & Prof. Malte Helmert
Textbook – The Famous AIMA Book
Major Technologies & Application Areas
Dramatic Progress over the Last Decade – NN
Dramatic Progress over the Last Decade - Search
What is AI !!
Humanly vs. Rationally || Thinking vs. Acting
Thinking Humanly
✔
This requires "getting inside" of the human mind to see how it works and then
comparing our computer programs to this,
✔
like what cognitive science attempts to do.
✔
Another way to do this is to observe a human problem solving and argue that
one's programs go about problem solving in a similar way.
✔
Not important: Being able to solve problems correctly.
✔
Important: Being able to solve problems like a human would.
✔
Example: GPS (General Problem Solver) was an early computer program that
attempted to model human thinking. The developers were not so much interested
in whether or not GPS solved problems correctly. They were more interested in
showing that it solved problems like people, going through the same steps and
taking around the same amount of time to perform those steps.
✔
This is what cognitive science and cognitive psychology attempt to do.
✔
Introspection (observing ourselves); Psychological experiments; Brain
research.
Acting Humanly

To pass this test requires:

A total Turing test would also require:


Thinking Rationally
✔
Aristotle was one of the first to attempt to codify "thinking".
✔
His syllogisms provided patterns of argument structure that always gave
correct conclusions, giving correct premises.
✔
Example: All computers use energy. Using energy always generates heat.
Therefore, all computers generate heat.
✔
This initiate the field of logic.
✔
By 1965, programs existed that could, given enough time and memory, take a
description of the problem in logical notation and find the solution, if one
existed.
✔
There are two main obstacles to this approach:
✔
it is difficult to make informal/commonsense knowledge precise enough to use
the logicist approach particularly when there is uncertainty in the knowledge.
✔
there is a big difference between being able to solve a problem in principle
and doing so in practice.
Acting Rationally
✔
Acting rationally means acting so as to achieve one's goals, given one's beliefs.
✔
Rational thinking is a prerequisite for rational acting, although it is not a
necessary condition
✔
what to do, for example, when we must make a decision faced with insufficient
information? e.g., reflex actions.
✔
The study of AI as rational agent design has two advantages:
✔
It is more general than the logical approach because correct inference is only a
useful mechanism for achieving rationality, not a necessary one.
✔
It is more amenable to scientific development than approaches based on
human behaviour or human thought because a standard of rationality can be
defined independent of humans.
✔
Achieving perfect rationality in complex environments is not possible because the
computational demands are too high. However, we will study perfect rationality as
a starting place.
Nature of Intelligence
Machine vs Human
✔
Machines have far superior computational abilities than humans
✔
Square root of 964,324 ?
✔
Machines can sort through enormous amounts of data.
✔
While a doctor makes a diagnosis in ~10 minutes, AI system makes a million.
✔
Humans, in general, are good at ?
Scene Understanding Taxi Driving
Dialogue Processing Identify the digits

Ping-Pong playing robot


Learn Cook from youtube
Perform clustering
Machine
Learning
Algorithms
Machine Learning Applications
Why not allow machines to do the heavy thinking for us in order to make better
decisions that, in general, people do better ?
Problems Deep Learning cannot Solve
Planning & Scheduling: Field of AI
Planning & Scheduling: Field of AI
Games
Planning & Scheduling: Field of AI
Planning & Scheduling: Field of AI
Planning & Scheduling: Field of AI
Planning & Scheduling: Field of AI
Solving Real-World Problems

Modeling
(Statistics / D.Tree / D.Graph / Logics / Constraint/ PDDL)
+
Solving
(Reasoning with Rules / Search with Heuristics)
Solving Real-World Problems

Credit: A. Lokketangen
Solving Real-World Problems
Find shortest route

Formulate Abstract Problem

Solve the Abstract Problem

Credit: MIT, USA


8-Puzzle Problem
Goal

Credit: MIT, USA


8-Puzzle Problem
Heuristics

Credit: MIT, USA


Chess Problem | Strategic Search

Credit: MIT, USA


N-Queen Problem | Local Search

Goal

Local Search:
Solving Linguistic Problems
✔
Jack owns a dog.
✔
Every dog owner is an animal lover.
✔
No animal lover kills an animal.
✔
Either Jack or Curiosity killed the cat, who is named Tuna.
✔
Did Curiosity kill Tuna?

FOL Representation Solving by reasoning (resolution)


A. (x) (Dog(x)  Owns(Jack,x))
B. (x) (((y) (Dog(y)  Owns(x, y)))  AnimalLover(x))
C. (x) (AnimalLover(x)  ((y) Animal(y)  Kills(x,y)))
D. Kills(Jack,Tuna)  Kills(Curiosity,Tuna)
E. Cat(Tuna)
F. (x) (Cat(x)  Animal(x) )
G. Kills(Curiosity, Tuna) Goal

29
Automated Planning (Modeling+Solving)

8-Puzzle Problem Block-World


Automated Planning (Modeling: PDDL)
Domain.pddl

A
C B
B A C
Problem.pddl init goal
Solution
1) move C A Table
2) move B Table C
3) move A Table B
Automated Planning (Modeling: PDDL)
Domain.pddl

Problem.pddl
Constraint Satisfaction (Modeling: MiniZinc)

AED.mzn

AED.dzn

solution
Discrete Optimisation (Modeling: MiniZinc)

Maximize the total


happiness of the celebrities
marriage.mzn

solution

You might also like