Scribd
Upload
21 views19 pages

Chapter 1 AI

Uploaded by

Sã Mï
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
21 views19 pages

Chapter 1 AI

Uploaded by

Sã Mï
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 19

FUNDAMENTALS OF

ARTIFICIAL INTELLIGENCE

CHAPTER ONE -INTRODUCTION TO


ARTIFICIAL INTELLIGENCE
2 CONTENTS

 Introduction to AI.
 Objectives/Goals of AI
 What is AI?
 Approaches to AI – making computer:
 Think like a human (Thinking humanly)
 Act like a human (Acting humanly)
 Think rationally (Thinking rationally)
 Act rationally (Acting rationally)

 The Foundations of AI Bits of History and the State of the Art


3 INTRODUCTION TO AI.

 Intelligence
 Intelligence is the capability of observing, learning, remembering & reasoning.
 The ability to learn and solve problems.
 AI attempts to develop intelligent agents.
 AI has produced many significant and impressive products even at this early stage in its
development.
 AI is one of the newest disciplines.
 It was formally initiated in 1956.
4 INTRODUCTION TO AI.

 AI currently encompasses a huge variety of subfields, from general-purpose areas such as


perception and logical reasoning, to specific tasks such as playing chess, proving mathematical
theorems, writing poetry, and diagnosing diseases.
 Often, scientists in other fields move gradually into artificial intelligence, where they find the
tools and vocabulary to systematize and automate the intellectual tasks on which they have
been working all their lives.
 AI is the study of intelligent behavior and
 AI is also concerned with the implementation of a computer program which exhibits
intelligent behavior.
5 WHAT IS AI?

 Artificial Intelligence
 refers to the simulation of human intelligence in machines that are programmed to think and
act like humans.
 Methods for applying computers to problems that require “intelligence”
 Study of the fundamental limits of “intelligent” behavior by computers
 Artificial intelligence (AI) refers to systems that display intelligent behavior by analyzing their
environment and taking actions
 Artificial intelligence is intelligence demonstrated by machines, unlike the natural intelligence
displayed by humans and animals, which involves consciousness and emotionality.
6 WHAT IS AI?

 The intelligence is intangible. It is composed of:


 Reasoning
 Learning
 Problem Solving
 Perception
 Linguistic Intelligence
 Objectives of AI works are reasoning, knowledge representation, planning, learning, natural
language processing, realization, and ability to move and manipulate objects.
7 WHAT IS AI?

 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.
8 APPROACHES TO AI

 Approaches of AI fall into four categories:


 Making computer

Thinking humanly Thinking rationally

Acting humanly Acting rationally

 AI deals with:
 various kinds of knowledge representation schemes,
 different techniques of intelligent search
 various methods for resolving uncertainty of data knowledge
 different schemes for automated machine learning and many others
9 APPROACHES TO AI

 1. Think like a human: 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
the 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.
10 APPROACHES TO AI

 2. Act like a human: The Turing Test


 Can machines act like human do?
 Can machines behave intelligently?
 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, language understanding, learning
11 APPROACHES TO AI

 3. Think rationally: The Laws of Thought


 A system is rational if it thinks/does the right thing through correct 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
 These Laws of thought governed the operation of the mind and initiated the field of Logic.
12 APPROACHES TO AI

 4. Acting rationally: The rational agent Approach


 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
13 APPROACHES TO AI

 4. Acting rationally: The rational agent Approach


 Making a computer act rationally
 An agent is just something that perceives and acts.
 Rational behavior: doing “the right thing”.
 “The right thing”: which is expected to maximize goal achievement, given the available
information.
 Doesn't necessarily involve thinking – e.g., blinking reflex – but thinking should be in the
service of rational action.
 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).
14 WHY AI?

 "AI can have two purposes”


 One is to use the power of computers to augment human thinking,
 just as we use motors to augment human or horse power
 Robotics and expert systems are major branches of that.
 The other is to use a computer's artificial intelligence to understand how humans think in a
humanoid way.
15 WHY AI?

 AI works include
 Natural Language Processing - to enable it to communicate successfully in English (or some
other human language);
 Knowledge Representation - to store information provided before or during the interrogation;
 Automated Reasoning - to use the stored information to answer questions and to draw new
conclusions;
 Machine learning - to adapt to new circumstances and to detect and extrapolate patterns.
 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)
16 WHY AI?
17 THE FOUNDATIONS OF AI

 Philosophy (428 B . C .-present)


 Can formal rules be used to draw valid conclusions?
 How does the mental mind arise from a physical brain?
 Dualism: there is a part of the mind (or soul or spirit) that is outside of nature, exempt from
physical laws
 Materialism: holds that all the world (including the brain and mind) operate according to
physical law.
 Where does knowledge come from?
 Empiricism
 Induction
 How does knowledge lead to action?
18 THE FOUNDATIONS OF AI

 Neuroscience (1861-present)
 How do brains process information?
 Psychology (1879-present)
 How do humans and animals think and act?
 Computer engineering (1940-present)
 How can we build an efficient computer?
 Control theory and Cybernetics (1948-present)
 How can artifacts operate under their own control?
 Linguistics (1957-present)
 How does language relate to thought? And Others
19 APPLICATIONS OF AI

 What can AI do today?


 Autonomous planning and scheduling.
 Game playing.
 Autonomous control.
 Diagnosis: Medical diagnosis programs.
 Logistics Planning.
 Robotics.
 AI in agriculture
 Language understanding and problem solving. etc

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy