An-Najah Staff

Course title and number

Artificial Intelligence and Machine Learning - 66417

Instructor(s) name(s)

Anas Tomeh

Contact information

tomeh@najah.edu. Office: 1360

Semester and academic year

First Semester 2010/2011

Compulsory / Elective

Elective

Prerequisites

Data Structure an algorithms

Course

Contents

(description)

Introduction

• What is AI
• The Foundations of Artificial Intelligence
• The History of Artificial Intelligence

Intelligent Agents

• How Agents Should Act
• Structure of Intelligent Agents
• Environments

Problem Solving by Searching

• Problem-Solving Agents
• Example Problems
• Searching for Solutions
• Search Strategies
• Constraint Satisfaction Search
• Genetic Algorithms

Informed Search Methods

• Best-First Search
• Heuristic Functions
• Memory Bounded Search
• Iterative Improvement Algorithms

Games

• Games as Search Problems
• Two-Person Games
• Alpha-Beta Pruning
• Games That Include an Element of Chance
• State-of-the-Art Game Programs

Knowledge and Reasoning

• A Knowledge-Based Agent
• Representation, Reasoning, and Logic
• Prepositional Logic

First Order Logic

• Syntax and Semantics
• Extensions and Notational Variations
• Using First-Order Logic
• A Simple Reflex Agent
• Representing Change in the World
• Toward a Goal-Based Agent

Inference in First-Order Logic

• Inference Rules Involving Quantifiers
• Generalized Modus Ponens
• Forward and Backward Chaining
• Resolution: A Complete Inference Procedure

Prolog

Fuzzy Logic

• fuzzy groups
• fuzzy logic
• fuzzy relations
• fuzzy graphs
• fuzzy logic system design

Learning from Observations

• A General Model of Learning Agents
• Inductive Learning
• Learning Decision Trees
• Using Information Theory

Learning in Neural Networks

• How the Brain Works
• Neural Networks
• Perceptrons
• Multilayer Feed-Forward Networks
• Applications of Neural Networks

Course Objectives

• Formulate and assess problems in artificial intelligence.
• Assess the strengths and weaknesses of several methods for representing knowledge.
• Assess the strengths and weaknesses of several AI algorithms in areas such as heuristic search, game search, logical inference, statistical inference, decision theory, planning, machine learning, neural networks, and natural language processing.
• Developing creative capacities for the design, implementation, and analysis of computer programs that reason and/or act intelligently.
• Implement software solutions to a wide-variety of problems generally considered to require artificial intelligence.

Intended learning

Outcomes and

Competences

At the end of this course students should be able to;

• Know classical examples of artificial intelligence
• Know characteristics of programs that can be considered "intelligent"
• Understand the use of heuristics in search problems and games
• Know a variety of ways to represent and retrieve knowledge and information
• Know the fundamentals of artificial intelligence programming techniques in a modern programming language
• Explain the concepts of decision tree, fuzzy logic, and neural networks.

Textbook and  References

Artificial Intelligence: A Modern Approach 3^rd Edition - Stuart Russell and Peter Norvig, Prentice Hall.

Assessment Criteria

Activity

Percent (%)

Midterm Exams

40

Homework and  quizzes

10

Other criteria (Research, Discussion..etc)

5

Final Exam

45

Week

Subject

1

Introductionand Intelligent Agents

2

Problem Solving by Searching

3

4

Informed Search Methods

5

6

Games

7

MIDTERM EXAM 1

8

Knowledge and Reasoning

9

First Order Logic

10

Inference in First-Order Logic

11

Prolog

12

Fuzzy Logic

13

MIDTERM EXAM 2

14

Learning from Observations

15

Learning in Neural Networks

16

Final Exam