COURSE SYLLABUS

ARTIFICIAL INTELLIGENCE THEORY

1	Course Title:	ARTIFICIAL INTELLIGENCE THEORY
2	Course Code:	BM5116
3	Type of Course:	Optional
4	Level of Course:	Second Cycle
5	Year of Study:	1
6	Semester:	2
7	ECTS Credits Allocated:	6
8	Theoretical (hour/week):	3
9	Practice (hour/week) :	0
10	Laboratory (hour/week) :	0
11	Prerequisites:	None
12	Recommended optional programme components:	None
13	Language:	Turkish
14	Mode of Delivery:	Face to face
15	Course Coordinator:	Dr. Ögr. Üyesi CEYDA NUR ÖZTÜRK
16	Course Lecturers:
17	Contactinformation of the Course Coordinator:	ceydanur@uludag.edu.tr
18	Website:
19	Objective of the Course:	To explain the representations, techniques, methods, and tools for making computer systems equipped with the abilities of problem solving, inference, learning, decision making, and planning in various environments.
20	Contribution of the Course to Professional Development	Engineering Science: 70%, Engineering Design: 30%

Learning Outcomes:

1	Being able to solve problems using uninformed, informed, local, or adversarial search methods;
2	Being able to satisfy initially described certain constraints during a search;
3	Being able to program logical inference problems using declarative languages;
4	Being able to select appropriate learning methods for classification, regression, or clustering problems;
5	Being able to adapt probabilistic reasoning approaches to real world problems;
6	Having knowledge about fundamentals of deep learning;
7	Being able to design and implement intelligent systems that can work in different environments;

22	Course Content:

Week	Theoretical	Practical
1	Introduction, intelligent agents
2	Problem solving by searching, uninformed search algorithms
3	Informed search algorithms, local search algorithms
4	Games and adversarial search
5	Constraint satisfaction problems
6	Logical inference: Propositional logic, first-order logic
7	Prolog programming
8	Planning, forward and backward searches, planning in real world
9	Probabilistic reasoning: uncertainty, Bayes’ rule, Bayesian networks
10	Temporal probabilistic reasoning: hidden Markov models, forward algorithm, Viterbi algorithm, forward and backward algorithm
11	Learning from observations: linear and logistic regressions, decision trees, design and analysis of learning systems
12	Statistical learning: Bayesian learning, naive Bayes, nearest neighbour models, artificial neural networks, backpropagation algorithm
13	Deep learning
14	Decision making: Markov decision processes, value iteration, reinforcement learning

23	Textbooks, References and/or Other Materials:	1. Russell, S., and Norvig, P., 2016. Artificial Intelligence: A Modern Approach, 3rd Edition, Pearson Education, ISBN-10: 0136042597 ISBN-13: 978-1292153964. 2. Zhang, A., Lipton, Z. C., Li, M., and Smola, A. J., 2022. Dive into deep learning. arXiv preprint DOI: https://doi.org/10.48550/arXiv.2106.11342. 3. Ekman, M., 2021. Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, NLP, and Transformers Using TensorFlow, Addison-Wesley Professional, ISBN-10: 0137470355 ISBN-13: 978-0137470358.
24	Assesment

TERM LEARNING ACTIVITIES	NUMBER	PERCENT
Midterm Exam	0	0
Quiz	0	0
Homeworks, Performances	3	60
Final Exam	1	40
Total	4	100
Contribution of Term (Year) Learning Activities to Success Grade		60
Contribution of Final Exam to Success Grade		40
Total		100
Measurement and Evaluation Techniques Used in the Course	Programming assignments, article review, presentation, written exam
Information

ECTS / WORK LOAD TABLE

CONTRIBUTION OF LEARNING OUTCOMES TO PROGRAMME QUALIFICATIONS

LO: Learning Objectives

PQ: Program Qualifications

Contribution Level:

1 Very Low

2 Low

3 Medium

4 High

5 Very High