TÜRKÇE
ENGLISH
Information
| Code | BL237 |
| Name | Artificial Intelligence Applications |
| Term | 2023-2024 Academic Year |
| Semester | 3. Semester |
| Duration (T+A) | 2-1 (T-A) (17 Week) |
| ECTS | 3 ECTS |
| National Credit | 2 National Credit |
| Teaching Language | Türkçe |
| Level | Ön Lisans Dersi |
| Type | Normal |
| Label | C Compulsory |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Öğr. Gör. Mahir ATMIŞ |
| Course Instructor |
Öğr. Gör. Mahir ATMIŞ
(A Group)
(Ins. in Charge)
|
Course Goal / Objective
To test the machine learning methods used in our age on current data.
Course Content
"Introduction and definitions, classification/regression problem, supervised learning, inear regression, the smallest squares of error, logistics regression, perceptron, bias-variance, feature selection, artificial neural networks, decision trees, support vector machines, unsupervised learning"
Course Precondition
None
Resources
Lecture Notes Mahir Atmış
Notes
Uygulamalar ile Python ve Yapay Zeka, Emrah Aydemir
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Explains the concept of Artificial Intelligence and algorithms. |
| LO02 | Explains the concept of Artificial Neural Networks and deep networks. |
| LO03 | Teachs the concepts of supervision and unsupervised learning. |
| LO04 | Teaches the concepts of clustering. |
| LO05 | Tests learning algorithms on ready data sets. |
| LO06 | Understands the basic logic of learning algorithms. |
| LO07 | Uses state of the art learning algorithms. |
| LO08 | Develops their own learning algorithm. |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | Explain the basic scientific concepts related to Computer Technologies. | |
| PLO02 | Beceriler - Bilişsel, Uygulamalı | Can use algorithmic thinking & planning approaches in programming. | |
| PLO03 | Beceriler - Bilişsel, Uygulamalı | uses word processor, spreadsheet, presentation programs. | |
| PLO04 | Bilgi - Kuramsal, Olgusal | Has the ability to solve problems in the field of computer programming. | 5 |
| PLO05 | Bilgi - Kuramsal, Olgusal | Knows the basic electronic parts of computer hardware and their functioning. | |
| PLO06 | Beceriler - Bilişsel, Uygulamalı | Basic level Database Systems, client/server software and implements | |
| PLO07 | Beceriler - Bilişsel, Uygulamalı | In Computer Technologies, students use graphical programs used in interface design and 3D modeling in web pages at basic level. | |
| PLO08 | Beceriler - Bilişsel, Uygulamalı | Explains, designs and installs network systems. | |
| PLO09 | Yetkinlikler - Alana Özgü Yetkinlik | Uses Internet technologies, develops server-side working internet applications. | |
| PLO10 | Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği | Can carry out a basic study related to the field independently or in disciplined teams | |
| PLO11 | Yetkinlikler - Öğrenme Yetkinliği | Can do resource research and obtain information from database in order to follow the developments in the field with the necessity of lifelong learning. | |
| PLO12 | Bilgi - Kuramsal, Olgusal | Knows a foreign language which is sufficient for the applications in the field. | |
| PLO13 | Bilgi - Kuramsal, Olgusal | To be able to communicate effectively in written and oral Turkish. | |
| PLO14 | Yetkinlikler - İletişim ve Sosyal Yetkinlik | He/she can clearly explain the designs and applications related to computer technologies to his colleagues, superiors, others who are related to the field or not. | 4 |
| PLO15 | Bilgi - Kuramsal, Olgusal | Has knowledge about Atatürk's Principles and History of Revolution. | |
| PLO16 | Yetkinlikler - İletişim ve Sosyal Yetkinlik | It is aware of occupational health and safety, environmental and ethical values within the framework of global and social values. |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | What's Learning? | Preparation is not required. | |
| 2 | Clustering algorithms | Preparation is not required. | |
| 3 | Classification algorithms | Preparation is not required. | |
| 4 | Regression | Preparation is not required. | |
| 5 | Decision Trees | Preparation is not required. | |
| 6 | Support Vector Machines | Preparation is not required. | |
| 7 | Bayes Classification | Preparation is not required. | |
| 8 | Mid-Term Exam | ||
| 9 | Artificial Neural Networks | Preparation is not required. | |
| 10 | Artificial Neural Networks (continuation) | Preparation is not required. | |
| 11 | Convolutional Neural Networks | Preparation is not required. | |
| 12 | Convolutional Neural Networks (continuation) | Preparation is not required. | |
| 13 | Reinforcement Learning | Preparation is not required. | |
| 14 | Unsupervised Learning | Preparation is not required. | |
| 15 | Unsupervised Learning (continuation) | Preparation is not required. | |
| 16 | Term Exams | ||
| 17 | Term Exams |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
| Out of Class Study (Preliminary Work, Practice) | 14 | 2 | 28 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 1 | 2 | 2 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 5 | 5 |
| Final Exam | 1 | 10 | 10 |
| Total Workload (Hour) | 87 | ||
| Total Workload / 25 (h) | 3,48 | ||
| ECTS | 3 ECTS | ||