APT3010

APT3010-INTRODUCTION TO ARTIFICIAL INTELLIGENCE
Course Description
Prerequisite - APT1020
This is an introductory course on Artificial Intelligence. The main purpose of

this course is to provide the most fundamental knowledge to the students so
that they can understand what the AI is with minimal theoretic proofs and
formal notations to enable students to get the full picture of AI easily. AI
techniques and algorithms for solving those problems will be examined.
Students will learn about the methods and tools that will allow them to build
complete systems that can interact intelligently with their environment by
learning and reasoning about the world. Programming languages such as Lisp,
Python, and Theano among others may be used.
Link to university mission outcomes & to program learning outcomes
Aligned to the following university

mission outcomes:
CLO
Global understanding and
multicultural perspective
Preparedness for career
Leadership and Ethics

Higher order thinking
Community service
Literacy
1. Describe Artificial Intelligence   

Techniques
2. Design intelligent artifacts   
3. Implementing intelligent   
programs using logic
programming.
4. Recognize the limitations of   

current Artificial Intelligence
techniques.
Link to Program Learning Outcomes
PLO PLO 1 PLO PLO 3 PLO 4 PLO 5 PLO 6 PLO 7

2
Develop Conc Demon Write Explain Exhibit Develop
integrat eptu strate progra the profess skills to use
ed alize compet ms concepts ional tools,
softwar and ence in using underlyi behavi techniques
e for impl the use moder ng or and and
busines emen of n compute ethics application
ses/org t moder progra r skills in one
anizatio integ n mming informat of the
ns/insti rated comput langua ion following
tutions syste er tools ges specializatio
using ms and ns:
modern Techni Computer
techniq ques Networks
ues technology;
Distributed
and mobile
computing;
APT3010 B I I B
-
INTROD
UCTION
TO
ARTIFIC
IAL
INTELLI
GENCE
Course learning outcomes
By the end of the course the student should be able to:
1. Describe Artificial Intelligence Techniques

2. Design intelligent artifacts
3. Implementing intelligent programs using logic programming.
4. Recognize the limitations of current Artificial Intelligence techniques.
Course content
Week 1 Artificial Intelligence
1 Introduction
2 Intelligent Agents
Week 2 Problem Solving
3 Solving Problems by Searching
4 Beyond Classical Search
Week 3 5 Adversarial Search
6 Constraint Satisfaction Problems
Week 4 Knowledge and Reasoning
7 Logical Agents
8 First-Order Logic
9 Inference in First-Order Logic
Week 5 10 Classical Planning
11 Planning and Acting in the Real World
12 Knowledge Representation
Week 7 Uncertain Knowledge and Reasoning
13 Quantifying Uncertainty
14 Probabilistic Reasoning
Week 8 15 Probabilistic Reasoning over Time
16 Making Simple Decisions
17 Making Complex Decisions
Week 8 Part V Learning

18 Learning from Examples
Week 10 19 Knowledge in Learning
20 Learning Probabilistic Models
21 Reinforcement Learning
22 Game playing
Week 11 Communicating, Perceiving, and Acting
23 Natural Language Processing
Week 12 24 Natural Language for Communication
25 Perception
Week 13 26 Robotics
27 Computer Vision
Teaching methods
The course will be conducted through lectures, illustrations using computers,

and practical labs exercises. Students are required to participate in group
discussion, hands-on lab exercises and presentation to reinforce their
understanding of the concepts learnt and their application to common AI
programming tools in the industry
Recommended Text
Course Text:
 Artificial Intelligence: A Modern Approach Third Edition by Russell &

Norvig, 2010. Pearson Education Inc., ISBN:978-0-13-604259-4
Recommended Reading:
 Ethem Alpaydin,MIT Press, 2010ISBN:978-0-262-01243-0

1. Evaluation
Assignments & Lab Exercises 25%
Participation 5%
Quizzes 20%
Mid-Semester Exam 20%
Final Exam 30%

Total 100%
2. Key Institutional Academic Policies
Students should note the following are key policies as outlined in the
University Catalogue and Students Handbook
1. Academic dishonesty
a. Any intentional giving or use of external assistance during an
examination without the express permission of the faculty member
giving the examination.
b. Fabrication: any falsification or invention of data, citation or other
authority in an academic exercise;
c. Plagiarism: any passing off of another's ideas, words, or work as
one's own;
d. Previously Submitted Work: presenting work prepared for and
submitted to another course;
2. Class Attendance
Students are expected to attend all classes. Upon being absent from five
classes in a 3 unit course, the instructor will give a student an “F” grade
for that course.
3. USIU grading
A 90 - 100
A- 87 - 89
B+ 84 - 86
B 80 - 83
B- 77 - 79
C+ 74 - 76
C 70 - 73
C- 67 - 69
D+ 64 - 66
D 62 - 63
D- 60 - 61
F 0 - 59

APT3010

Uploaded by

Copyright:

Available Formats

APT3010

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

APT3010

Uploaded by

Copyright:

Available Formats

APT3010-INTRODUCTION TO ARTIFICIAL INTELLIGENCE

This is an introductory course on Artificial Intelligence. The main purpose of

Link to university mission outcomes & to program learning outcomes

Aligned to the following university

Preparedness for career

Leadership and Ethics

1. Describe Artificial Intelligence   

2. Design intelligent artifacts   

4. Recognize the limitations of   

PLO PLO 1 PLO PLO 3 PLO 4 PLO 5 PLO 6 PLO 7

Course learning outcomes

By the end of the course the student should be able to:

1. Describe Artificial Intelligence Techniques

Week 1 Artificial Intelligence

Week 2 Problem Solving

3 Solving Problems by Searching

4 Beyond Classical Search

Week 3 5 Adversarial Search

6 Constraint Satisfaction Problems

Week 4 Knowledge and Reasoning

9 Inference in First-Order Logic

Week 5 10 Classical Planning

11 Planning and Acting in the Real World

Week 7 Uncertain Knowledge and Reasoning

Week 8 15 Probabilistic Reasoning over Time

16 Making Simple Decisions

17 Making Complex Decisions

Week 8 Part V Learning

Week 10 19 Knowledge in Learning

20 Learning Probabilistic Models

Week 11 Communicating, Perceiving, and Acting

23 Natural Language Processing

Week 12 24 Natural Language for Communication

The course will be conducted through lectures, illustrations using computers,

 Artificial Intelligence: A Modern Approach Third Edition by Russell &

 Ethem Alpaydin,MIT Press, 2010ISBN:978-0-262-01243-0

Assignments & Lab Exercises 25%

Mid-Semester Exam 20%

Final Exam 30%

2. Key Institutional Academic Policies

You might also like