INTRODUCTION to AI

AIM

The objective of this course is to introduce and teach the fundamentals of problems, theories, algorithms and applications of Artificial Intelligence (AI). AI is a very fast-growning field that focuses on building intelligent systems that will have a great impact on every aera of industry, economy, and social life. The topics include definition and history of AI, problem solving via search, game playing, knowledge representation, propositional logic, first-order predicate logic, logical and probabilistic reasoning, planning, uncertain knowledge and reasoning, machine learning (popular machine learning algorithms, deep learning, reinforcement learning, and genetic algorithms), natural language processing, deep learning for natural language processing, computer vision and robotics.

CONTENT

This course contains; Introduction and Intelligent Agents,Problem Solving by Searching,Adversarial Search and Games,Constraint Satisfaction Problems,Logical Agents,First-Order Logic, Inference in First-Order Logic,Knowledge Representation, Automated Planning,Uncertain knowledge and reasoning,Exam week,Probabilistic Programming, Making Simple Decisions, Making Complex Decisions,Machine Learning,Deep Learning, Reinforcement Learning ,Natural Language Processing, Deep Learning for Natural Language Processing,Computer Vision, Robotics,Review and presentations.

1. 1

   Students will have an in-depth understanding of core areas of AI.

   Taught by: Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

2. 2

   Students will learn and gain an understanding of various search methods, knowledge representation, uncertainty, reasoning, machine learning, natural language processing, computer vision and robotics.

   Taught by: Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

3. 3

   Students will be able to choose the appropriate algorithm for solving an AI problem.

   Taught by: Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

4. 4

   Students will be introduced to the current research in artificial intelligence and encouraged to define research problems and develop effective solutions.

   Taught by: Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

WEEKLY PLAN

1. WEEK 1

   Introduction and Intelligent Agents

2. WEEK 2

   Problem Solving by Searching

3. WEEK 3

   Adversarial Search and Games

4. WEEK 4

   Constraint Satisfaction Problems

5. WEEK 5

   Logical Agents

6. WEEK 6

   First-Order Logic, Inference in First-Order Logic

7. WEEK 7

   Knowledge Representation, Automated Planning

8. WEEK 8

   Uncertain knowledge and reasoning

9. WEEK 9

   Exam week

10. WEEK 10

    Probabilistic Programming, Making Simple Decisions, Making Complex Decisions

11. WEEK 11

    Machine Learning

12. WEEK 12

    Deep Learning, Reinforcement Learning

13. WEEK 13

    Natural Language Processing, Deep Learning for Natural Language Processing

14. WEEK 14

    Computer Vision, Robotics

15. WEEK 15

    Review and presentations

ASSESSMENT

• Rate of Midterm Exam to Success30%
• Rate of Final Exam to Success70%

WORKLOAD

READING

• Artificial Intelligence: A Modern Approach, 4th Edition, by Stuart Russell and Peter Norvig, Pearson Education, 2021.
• - Speech and Language Processing by Jurafsky and Martin, 2021. - G. F. Luger, Artificial Intelligence, Addison-Wesley, 2002. - Lectures notes ve web resources in AI.

TEACHING STAFF

• Prof.Dr. Selim AKYOKUŞCOORDINATOR
• Prof.Dr. Selim AKYOKUŞ