The objective of this course is to train students so that they perceive Machine Learning algorithms in both logical and mathematical dimensions and develop these algorithms with a programming language within the framework of Artificial Intelligence concept.
Aim
Hands-On Machine Learning with Scikit-Learn and TensorFlow, Aurelien Geron (yazar), O'Reilly
Yapay Zeka: Dijital Hayalet
Turkish Edition | by Alexis Graf | Jan 1, 2023
Course Content
This course contains; Definition and History of Artificial Intelligence,Machine Learning,Machine Learning,Robotics,DEEP LEARNING MACHINE VISION,Data Preparation and Data Warehouses,BIG DATAKNOWLEDGE PRESENTATION,NATURAL LANGUAGE PROCESSING (NLP)TEXT MINING (TM)WEB MINING (WM)
,Ethical Issues of AI,Unsupervised Learning, Distance, Similarity, Centre of Graphs and AI,Statistical Learning and Model Selection.,Examples of Supervised - Unsupervised Learning Algorithms,Genetic Algorithm Concepts,Writing our own library for Python: Fuzzy C means algorithm, XİE BENI and
other unsupervised learning algorithms quality measures..
Dersin Öğrenme Kazanımları
Teaching Methods
Assessment Methods
1. Will be able to explainconcept of Artificial Intelligence.
16, 9
A
1.1. Tells artificial intelligence development.
9
D
1.2. Lists Artificial Intelligence Technologies.
13, 9
2. Will be able to explain the characteristics of intelligent systems.
16, 9
A
2.1. Compares the intelligent system examples used in business.
13
E
3. Will be able to identify Expert Systems.
13, 9
A
3.1. Tells the history of Expert Systems.
16, 9
3.2. Approaching the problems that need to be solved by knowing Expert Systems.
6, 9
4. Will be able to explain artificial neural networks.
13, 9
E
4.1. Defines the general properties of artificial neural networks.
9
4.2. Debates the working and learning principle of artificial neural networks.
9
E
4.3. Applies the most used models in Artificial Neural Networks.
6, 9
E
5. Will be able to compare the concepts of Supervised and Unsupervised Learning.
13, 9
D
5.1. Defines the concept of supervised learning.
16, 9
5.2. Defines the concept of unsupervised learning.
16, 9
6. Will be define the concept of Fuzzy Logic.
6, 9
D
6.1. Explains the Fuzzy Logic Controller Systems.
13, 9
6.2. Uses Fuzzy Logic Controller Applications.
13, 9
E
7. will be able to explain Genetic Algorithms.
9
A, E
7.1. Recognizes crossover, mutation and selection procedures used in algorithm.
6, 9
7.2. Recognizes Genetic Algorithm Applications.
2
F
Teaching Methods:
13: Case Study Method, 16: Question - Answer Technique, 2: Project Based Learning Model, 6: Experiential Learning, 9: Lecture Method
Assessment Methods:
A: Traditional Written Exam, D: Oral Exam, E: Homework, F: Project Task
Course Outline
Order
Subjects
Preliminary Work
1
Definition and History of Artificial Intelligence
2
Machine Learning
Related chapter in the course notes should be read.
3
Machine Learning
Related chapter in the course notes should be read.
4
Robotics
Related chapter in the course notes should be read.
5
DEEP LEARNING MACHINE VISION
6
Data Preparation and Data Warehouses
Reading and watching the related video
7
BIG DATAKNOWLEDGE PRESENTATION
8
NATURAL LANGUAGE PROCESSING (NLP)TEXT MINING (TM)WEB MINING (WM)
Related chapter in the course notes should be read.
9
Ethical Issues of AI
Reading and watching the related video
10
Unsupervised Learning, Distance, Similarity, Centre of Graphs and AI
11
Statistical Learning and Model Selection.
12
Examples of Supervised - Unsupervised Learning Algorithms
13
Genetic Algorithm Concepts
Related chapter in the course notes should be read.
14
Writing our own library for Python: Fuzzy C means algorithm, XİE BENI and
other unsupervised learning algorithms quality measures.
Prepare the Python environment
Resources
Yapay Zekâ;Disiplinlerarası Yaklaşımlar
Turkish Edition | by Banu Fulya Yıldırım | Jan 1, 2023
AFTER EACH LESSON A READING OR WATCHING TASK WILL BE GIVEN BY THE LECTURER.
Artificial Intelligence: Understanding Future's Language Kindle Edition by Umut Guney (Author) , 2023.
Course Contribution to Program Qualifications
Course Contribution to Program Qualifications
No
Program Qualification
Contribution Level
1
2
3
4
5
1
Defines the theoretical issues in the field of information and management.
2
Describes the necessary mathematical and statistical methods in the field of information and management.
X
3
Uses at least one computer program in the field of information and management.
X
4
Sustains proficiency in a foreign language requiredor information and management studies.
5
Prepares informatics/software projects and work in a team.
X
6
Constantly updates himself / herself by following developments in science and technology with an understanding of the importance of lifelong learning through critically evaluating the knowledge and skills that s/he has got.7. Uses theoretical and practical expertise in the field of information and management
7
Follows up-to-date technology using a foreign language at least A1 level, holds verbal / written communication skills.
8
Follows up-to-date technology using a foreign language at least A1 level, holds verbal / written communication.
9
Adopts organizational / institutional and social ethical values.
10
Within the framework of community involvement adopts social responsibility principles and takes initiative when necessary.
11
Uses and analyses basic facts and data in various disciplines (economics, finance, sociology, law, business) in order to conduct interdisciplinary studies.
X
12
Writes software in different platforms such as desktop, mobile, web on its own and / or in a team.
Assessment Methods
Contribution Level
Absolute Evaluation
Rate of Midterm Exam to Success
40
Rate of Final Exam to Success
60
Total
100
ECTS / Workload Table
Activities
Number of
Duration(Hour)
Total Workload(Hour)
Course Hours
15
3
45
Guided Problem Solving
4
1
4
Resolution of Homework Problems and Submission as a Report
7
5
35
Term Project
7
3
21
Presentation of Project / Seminar
1
12
12
Quiz
1
3
3
Midterm Exam
1
6
6
General Exam
1
12
12
Performance Task, Maintenance Plan
0
0
0
Total Workload(Hour)
138
Dersin AKTS Kredisi = Toplam İş Yükü (Saat)/30*=(138/30)
5
ECTS of the course: 30 hours of work is counted as 1 ECTS credit.
Detail Informations of the Course
Course Description
Course
Code
Semester
T+P (Hour)
Credit
ECTS
ARTIFICAL INTELLIGENCE
YBS3257520
Spring Semester
3+0
3
5
Course Program
Cuma 11:00-11:45
Cuma 12:00-12:45
Cuma 12:45-13:30
Prerequisites Courses
Recommended Elective Courses
Language of Course
Turkish
Course Level
First Cycle (Bachelor's Degree)
Course Type
Elective
Course Coordinator
Prof.Dr. Gökhan SİLAHTAROĞLU
Name of Lecturer(s)
Prof.Dr. Gökhan SİLAHTAROĞLU
Assistant(s)
The objective of this course is to train students so that they perceive Machine Learning algorithms in both logical and mathematical dimensions and develop these algorithms with a programming language within the framework of Artificial Intelligence concept.
Aim
Hands-On Machine Learning with Scikit-Learn and TensorFlow, Aurelien Geron (yazar), O'Reilly
Yapay Zeka: Dijital Hayalet
Turkish Edition | by Alexis Graf | Jan 1, 2023
Course Content
This course contains; Definition and History of Artificial Intelligence,Machine Learning,Machine Learning,Robotics,DEEP LEARNING MACHINE VISION,Data Preparation and Data Warehouses,BIG DATAKNOWLEDGE PRESENTATION,NATURAL LANGUAGE PROCESSING (NLP)TEXT MINING (TM)WEB MINING (WM)
,Ethical Issues of AI,Unsupervised Learning, Distance, Similarity, Centre of Graphs and AI,Statistical Learning and Model Selection.,Examples of Supervised - Unsupervised Learning Algorithms,Genetic Algorithm Concepts,Writing our own library for Python: Fuzzy C means algorithm, XİE BENI and
other unsupervised learning algorithms quality measures..
Dersin Öğrenme Kazanımları
Teaching Methods
Assessment Methods
1. Will be able to explainconcept of Artificial Intelligence.
16, 9
A
1.1. Tells artificial intelligence development.
9
D
1.2. Lists Artificial Intelligence Technologies.
13, 9
2. Will be able to explain the characteristics of intelligent systems.
16, 9
A
2.1. Compares the intelligent system examples used in business.
13
E
3. Will be able to identify Expert Systems.
13, 9
A
3.1. Tells the history of Expert Systems.
16, 9
3.2. Approaching the problems that need to be solved by knowing Expert Systems.
6, 9
4. Will be able to explain artificial neural networks.
13, 9
E
4.1. Defines the general properties of artificial neural networks.
9
4.2. Debates the working and learning principle of artificial neural networks.
9
E
4.3. Applies the most used models in Artificial Neural Networks.
6, 9
E
5. Will be able to compare the concepts of Supervised and Unsupervised Learning.
13, 9
D
5.1. Defines the concept of supervised learning.
16, 9
5.2. Defines the concept of unsupervised learning.
16, 9
6. Will be define the concept of Fuzzy Logic.
6, 9
D
6.1. Explains the Fuzzy Logic Controller Systems.
13, 9
6.2. Uses Fuzzy Logic Controller Applications.
13, 9
E
7. will be able to explain Genetic Algorithms.
9
A, E
7.1. Recognizes crossover, mutation and selection procedures used in algorithm.
6, 9
7.2. Recognizes Genetic Algorithm Applications.
2
F
Teaching Methods:
13: Case Study Method, 16: Question - Answer Technique, 2: Project Based Learning Model, 6: Experiential Learning, 9: Lecture Method
Assessment Methods:
A: Traditional Written Exam, D: Oral Exam, E: Homework, F: Project Task
Course Outline
Order
Subjects
Preliminary Work
1
Definition and History of Artificial Intelligence
2
Machine Learning
Related chapter in the course notes should be read.
3
Machine Learning
Related chapter in the course notes should be read.
4
Robotics
Related chapter in the course notes should be read.
5
DEEP LEARNING MACHINE VISION
6
Data Preparation and Data Warehouses
Reading and watching the related video
7
BIG DATAKNOWLEDGE PRESENTATION
8
NATURAL LANGUAGE PROCESSING (NLP)TEXT MINING (TM)WEB MINING (WM)
Related chapter in the course notes should be read.
9
Ethical Issues of AI
Reading and watching the related video
10
Unsupervised Learning, Distance, Similarity, Centre of Graphs and AI
11
Statistical Learning and Model Selection.
12
Examples of Supervised - Unsupervised Learning Algorithms
13
Genetic Algorithm Concepts
Related chapter in the course notes should be read.
14
Writing our own library for Python: Fuzzy C means algorithm, XİE BENI and
other unsupervised learning algorithms quality measures.
Prepare the Python environment
Resources
Yapay Zekâ;Disiplinlerarası Yaklaşımlar
Turkish Edition | by Banu Fulya Yıldırım | Jan 1, 2023
AFTER EACH LESSON A READING OR WATCHING TASK WILL BE GIVEN BY THE LECTURER.
Artificial Intelligence: Understanding Future's Language Kindle Edition by Umut Guney (Author) , 2023.
Course Contribution to Program Qualifications
Course Contribution to Program Qualifications
No
Program Qualification
Contribution Level
1
2
3
4
5
1
Defines the theoretical issues in the field of information and management.
2
Describes the necessary mathematical and statistical methods in the field of information and management.
X
3
Uses at least one computer program in the field of information and management.
X
4
Sustains proficiency in a foreign language requiredor information and management studies.
5
Prepares informatics/software projects and work in a team.
X
6
Constantly updates himself / herself by following developments in science and technology with an understanding of the importance of lifelong learning through critically evaluating the knowledge and skills that s/he has got.7. Uses theoretical and practical expertise in the field of information and management
7
Follows up-to-date technology using a foreign language at least A1 level, holds verbal / written communication skills.
8
Follows up-to-date technology using a foreign language at least A1 level, holds verbal / written communication.
9
Adopts organizational / institutional and social ethical values.
10
Within the framework of community involvement adopts social responsibility principles and takes initiative when necessary.
11
Uses and analyses basic facts and data in various disciplines (economics, finance, sociology, law, business) in order to conduct interdisciplinary studies.
X
12
Writes software in different platforms such as desktop, mobile, web on its own and / or in a team.
