Information Systems Engineering
Bachelor	TR-NQF-HE: Level 6	QF-EHEA: First Cycle	EQF-LLL: Level 6

Ders Genel Tanıtım Bilgileri

Course Code:

FET404

Ders İsmi:

Artificial Intelligence Mathematics

Ders Yarıyılı:

Fall

Ders Kredileri:

Theoretical	Practical	Laboratory	ECTS
2	1	0	5

Language of instruction:

Turkish

Ders Koşulu:

Ders İş Deneyimini Gerektiriyor mu?:

Yes

Type of course:

Bölüm Seçmeli

Course Level:

Bachelor

TR-NQF-HE:6. Master`s Degree

QF-EHEA:First Cycle

EQF-LLL:6. Master`s Degree

Mode of Delivery:

E-Learning

Course Coordinator :

Asst. Prof. Dr. SEDA KARATEKE

Course Lecturer(s):

Asst. Prof. Dr. TAYMAZ AKAN

Course Assistants:

Dersin Amaç ve İçeriği

Course Objectives:

This course will highlight the need for mathematical concepts by pointing directly to their usefulness in the context of basic Artificial Intelligence learning problems, and by emphasizing the mathematical foundations of basic Artificial Intelligence concepts; It aims to narrow the skill gap or even close it completely by gathering information in one place.

Course Content:

Matrices and Systems of Linear Equations and their solutions, Gradient, local/spherical maximum and minimum, saddle point, convex functions, gradient descent algorithms - batch, mini-stack, stochastic, performance comparisons, Classical and convex optimization, Central Machine Learning Problems/Data analysis and Models, Central Machine Learning Problems/Linear Regression, Numerical computation, Boolean Algebra and Decision Trees, Algorithms and Statistics, Artificial Intelligence Case Studies.

Learning Outcomes

The students who have succeeded in this course;

Learning Outcomes

1 - Knowledge
Theoretical - Conceptual
1) Explains the parameters and structure of different machine learning algorithms in machine learning using linear algebra. Understands that linear algebra is a must for understanding how neural networks are put together and how they work.
2) Understands the computational efficiency and scalability of machine learning algorithms
2 - Skills
Cognitive - Practical
1) Uses Vector Analysis to complete the artificial Intelligence (Machine learning) learning part.
3 - Competences
Communication and Social Competence
Learning Competence
1) Uses probability theories and applications to make assumptions about the underlying data when designing deep learning or artificial intelligence algorithms.
Field Specific Competence
1) Uses further theoretical and structural knowledge acquired in different fields of mathematical, computational, physical and economic sciences as a basis for the understanding and design of some modern AI tools and their application to natural and fundamental fields.
Competence to Work Independently and Take Responsibility

Ders Akış Planı

Week	Subject	Related Preparation
1)	Introduction and Motivation	Lecture Notes
2)	Mathematics Fundamentals/Linear Algebra > Matrices and Systems of Linear Equations and their solutions	Lecture Notes
3)	Mathematics Fundamentals/Linear Algebra> Vector Spaces and Linear Independence	Lecture Notes
4)	Mathematics Fundamentals/Matrix Decompositions>Determinants, Eigenvalues and Eigenvectors	Lecture Notes
5)	Gradient, local/spherical maximum and minimum, saddle point, convex functions, gradient descent algorithms - batch, mini-stack, stochastic, performance comparisons	Lecture Notes
6)	Vector Analysis	Lecture Notes
7)	Probability and Distributions	Lecture Notes
8)	Mid term	Lecture Notes
9)	Classical and convex optimization	Lecture Notes
10)	Center Machine Learning Problems/Data analysis and Models	Lecture Notes
11)	Central Machine Learning Problems/Linear Regression	Lecture Notes
12)	Numerical calculation	Lecture Notes
13)	Boolean Algebra and Decision Trees	Lecture Notes
14)	Algorithms and Statistics	Lecture Notes
15)	Final	Lecture Notes

Sources

Course Notes / Textbooks:

Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong, Mathematics for Machine Learning.

Dana H. Ballard, “An Introduction to Natural Computation”, Third Edition, MIT Press, 2000.

References:

1. https://towardsdatascience.com/the-mathematics-of-machine-learning-894f046c568
2. https://ocw.mit.edu/courses/mathematics/18-657-mathematics-of-machine-learning-fall-2015/lecture-notes/MIT18_657F15_LecNote.pdf
3. https://ichi.pro/tr/ai-ve-matematik-116112807338198
4. https://towardsdatascience.com/mathematics-for-ai-all-the-essential-math-topics-you-need-ed1d9c910baf
5. S. Haykin, "Neural Networks - A Comprehensive Foundation", Second Edition,Prentice Hall, 1999.

Ders - Program Öğrenme Kazanım İlişkisi

Ders Öğrenme Kazanımları	1	4	2	3	5
Program Outcomes

Ders - Öğrenme Kazanımı İlişkisi

No Effect	1 Lowest	2 Low	3 Average	4 High	5 Highest

Program Outcomes

Level of Contribution

Assessment & Grading

Semester Requirements	Number of Activities	Level of Contribution
total		%
PERCENTAGE OF SEMESTER WORK		% 0
PERCENTAGE OF FINAL WORK		%
total		%