Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
15 views

Lecture 1 Introduction

The document provides details about an advanced artificial intelligence and knowledge representation course, including learning objectives, required materials, grading policy, and an overview of lecture 1 on introductions to AI. Key topics covered include definitions of AI, the foundations of AI, applications of AI, intelligent agents and their interaction with environments, and rational vs goal-based agents.

Uploaded by

ezaat.shalby
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
15 views

Lecture 1 Introduction

The document provides details about an advanced artificial intelligence and knowledge representation course, including learning objectives, required materials, grading policy, and an overview of lecture 1 on introductions to AI. Key topics covered include definitions of AI, the foundations of AI, applications of AI, intelligent agents and their interaction with environments, and rational vs goal-based agents.

Uploaded by

ezaat.shalby
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 38

Advanced AI & Knowledge

Representation
Dr. Basma M. Hassan
Faculty of Artificial Intelligence
Kafr el-Sheikh University

2022/2023
Course Details

Course Code AI208 (core)


Course Name Advanced AI & Knowledge Representation
Coordinating Unit Department of Data Science,
Faculty of Artificial Intelligence, Kafr el-Sheikh
University
Term Semester 2
Level Undergraduate -Level 2
Learning Objectives of this Course
What you'll learn?

❑ This course gives a basic introduction to Artificial Intelligence

❑ Then, We will study the core topics of knowledge representation and reasoning

❑ Through an algorithmic approach, the students are given a practical understanding of


the methods being taught, in particular through making their own implementations of
several of the methods.
Course Materials

Required Resources: The prescribed textbooks for


the course are:

• Stuart J. Russell and Peter Norvig, "Artificial


Intelligence: A Modern Approach," 3rd Edition
(2010), by Pearson Education Inc.

• George F. Luger, "Artificial Intelligence: Structures


and strategies for complex problem solving, “5th
edition (2005), Pearson Education Limited.
Grading Policy
The Assessment for this subject consists of five components with the following
weightings

Final Written Exam 60


Group Project 10
Midterm Written Exam 10
Labs 10
Assignments/Sheets 10
Lecture 1:
Introduction
Definitions of AI
Thinking
Rationally

Thinking Acting
Humanly Rationally

Thinking
Humanly
Foundations of Artificial Intelligence
❖ Philosophy ❖ Economics
• Can formal rules be used to draw valid conclusions? • How should we make decisions so as to maximize
• How does the mind arise from a physical brain? payoff?
• Where does knowledge come from? • How should we do this when others may not go along?
• How does knowledge lead to action? • How should we do this when the payoff may be far in
the future?
❖ Mathematics
• What are the formal rules to draw valid conclusions? ❖ Computer Engineering
• What can be computed? • How can we build an efficient computer?
• How do we reason with uncertain information?
❖ Control theory and cybernetics
❖ Neuroscience • How can artifacts operate under their own control?
• How do brains process information?
❖ Linguistics
❖ Psychology • How does language relate to thought?
• How do humans and animals think and act?
The birth of AI
• McCarthy called for two months workshop at Dartmouth (1956).

• McCarthy invites Minsky, Claude Shannon, and Nathaniel Rochester.

• There were 10 attendees in all, including Trenchard More from


Princeton, Arthur Samuel from IBM, Ray Solomonoff, and Oliver
Selfridge from MIT.

• Newell and Simon stole the show by reasoning program, the Logic
Theorist (LT), about which Simon claimed, "We have invented a
computer program capable of thinking non-numerically, and thereby
solved the venerable mind—body problem.
An AI program is called an intelligent
agent.

Interacts with an environment in

Intelligent a state
Properties of an Uses sensors to perceive its state
Agent intelligent agent: Uses actuators to affect its state
Has a function called its control policy
that maps sensors to actuators

The process of this type of interaction is


called the perception action cycle
Intelligent Agent
Applications of AI
• AI has successfully been used in many applications such
as:

• Finance
• Robotics
• Games
• Medicine
• The web
AI in Finance
Trade Agent

Stock/Trade
Decisions
Markets
AI in Medicine
Diagnostics Agent

Patient-Doctor Decisions
AI in Robotics
Robot

Surrounding
Decisions
Environment
AI in the WEB
Search Text

Feeling
Search Lukey
Crawler (DB)

User+WWW Decisions
AI in Games
Game Agent

User/Player Decisions
Intelligent
Agents in the
World….
Example: Vacuum - Agent
Rational Agents
Task Environment (PEAS)
Autonomous Car (PEAS Example)
Spam Filter (PEAS Example)
Coal & Cost Agents
Goal-based Agents
Cost-based Agents
Cost-based Agents
Specifying the Task Environment
❖Environment Types
Fully Observable vs Partially Observal
Deterministic vs Stochastics vs Strategic
Episodic vs Sequential
Static vs Dynamic vs Semi-dynamic
Discreet vs Continuous
Single-Agent vs Multi-Agent
Known vs Unknown
Terminology
• Fully observable

• An environment is called fully observable if what your


agent can sense at any point in time is completely
sufficient to make the optimal decision (its sensors can
see the entire state of the environment).

• Partially observable:

• that contrasts with some other environments where


agents need memory to make the best decision.
Fully Observable vs. Partially
Observable
❖ Do the agent's sensors give it access to the complete state of the environment?
❖ For any given world state, are the values of all the variables known to the agent?
Deterministic vs. Stochastic (vs. Strategic)
❖ Is the next state of the environment completely determined by the current state and
the agent’s action?
❖ Is the transition model deterministic (unique successor state given current state and
action) or stochastic (distribution over successor states given current state and
action)
❖ Strategic the environment is deterministic except for the actions of other agents
Episodic vs. Sequential
❖ Is the agent’s experience divided into unconnected single decisions/actions, or is it a
coherent sequence of observations and actions in which the world evolves according
to the transition model?
Static vs. Dynamic (vs. Semi-dynamic)
❖ Is the world changing while the agent is thinking?
❖ Semi dynamic the environment does not change with the passage of time, but the
agent's performance score does
Discrete vs. Continuous
❖ Does the environment provide a fixed number of distinct percepts, actions, and
environment states?
❖ Are the values of the state variables discrete or continuous?
❖ Time can also evolve in a discrete or continuous fashion
Single Agent vs. Multi-Agent
❖ Is an agent operating by itself in the environment?
❖ Is the environment of an autonomous taxi driver a competitive multiagent
environment or a cooperative multiagent environment?
Known vs. Unknown
❖ Are the rules of the environment (transition model and rewards associated with
states) known to the agent
❖ Strictly speaking, not a property of the environment, but of the agent’s state of
knowledge
Examples of the different environments
Quiz

You might also like