TÜRKÇE
ENGLISH
Information
| Code | MTH001 |
| Name | Introduction to Artificial Intelligence (Cezeri) |
| Term | 2023-2024 Academic Year |
| Semester | 6. Semester |
| Duration (T+A) | 2-0 (T-A) (17 Week) |
| ECTS | 4 ECTS |
| National Credit | 2 National Credit |
| Teaching Language | Türkçe |
| Level | Lisans Dersi |
| Type | Normal |
| Mode of study | Uzaktan Öğretim |
| Catalog Information Coordinator | Prof. Dr. CENK ŞAHİN |
| Course Instructor |
1 2 |
Course Goal / Objective
The aim of the course is to introduce students to the field of artificial intelligence. provide information on basic methods and students to practice artificial intelligence methods use in solving problems to enable them to acquire skills.
Course Content
Python data structures, Numpy array operations, Data analysis applications with Pandas library, Regression with machine learning models and classification applications, evaluation metrics, hyperparameter adjustments, artificial neural networks, error functions, activation functions, forward and backward propagation, regression with deep learning models and classification applications
Course Precondition
There are no prerequisites for the course.
Resources
Artificial Intelligence A Modern Approach, S.Russell, P.Norvig Machine Learning Yearning, A. Ng Deep Learning, I. Goodfellow, Y.Bengio, A.Courville
Notes
open access resources
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Fundamentals of the Python programming language to learn |
| LO02 | Understanding the fundamental steps of data science |
| LO03 | Learn to analyze and process data |
| LO04 | In machine learning and deep learning mentality of the algorithms used. clutch |
| LO05 | Working principle of artificial neural networks clutch |
| LO06 | For different problems in artificial intelligence be able to design models and different models using learning problems implement solutions |
| LO07 | Analyze the outputs of AI models and models according to the results learn to set parameters |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | Have sufficient knowledge of mathematics, science and related engineering disciplines; can use the theoretical and applied knowledge in these fields in complex engineering problems. | 5 |
| PLO02 | Bilgi - Kuramsal, Olgusal | Acquire the ability to identify, define, formulate and solve complex Industrial Engineering problems; for this purpose, will have the ability to choose and apply appropriate analysis and modeling methods. | 5 |
| PLO03 | Bilgi - Kuramsal, Olgusal | Design a complex system, process, device or product to meet specific requirements under realistic constraints and conditions; can apply modern design methods for this purpose. | 4 |
| PLO04 | Bilgi - Kuramsal, Olgusal | Develops modern techniques and tools necessary for the analysis and solution of complex problems encountered in engineering applications, and has the ability to use information technologies effectively. | |
| PLO05 | Bilgi - Kuramsal, Olgusal | Have the ability to design experiments, collect data, analyze and interpret results for the investigation of complex engineering problems or discipline-specific research topics. | |
| PLO06 | Bilgi - Kuramsal, Olgusal | Have the ability to work effectively in disciplinary and multi-disciplinary teams or individually. | |
| PLO07 | Beceriler - Bilişsel, Uygulamalı | Ability to communicate effectively in Turkish orally and in writing; knowledge of at least one foreign language; have the ability to write effective reports and understand written reports, to prepare design and production reports, to make effective presentations, to give and receive clear and understandable instructions. | |
| PLO08 | Beceriler - Bilişsel, Uygulamalı | Have the awareness of the necessity of lifelong learning; can follow the developments in science and technology and have the ability to constantly renew themselves. | 4 |
| PLO09 | Yetkinlikler - Öğrenme Yetkinliği | Acts in accordance with ethical principles, has knowledge about the standards used in engineering applications with the awareness of professional and ethical responsibility. | |
| PLO10 | Yetkinlikler - Öğrenme Yetkinliği | Gain knowledge of business practices such as project management, risk management and change management; become aware of entrepreneurship and innovation. | |
| PLO11 | Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği | Gains knowledge about the effects of engineering practices on health, environment and safety in universal and social dimensions and the problems of the age reflected in the field of engineering and has awareness of the legal consequences of engineering solutions. | |
| PLO12 | Yetkinlikler - Öğrenme Yetkinliği | They can benefit from the power of effective communication in their professional life and have the ability to interpret developments correctly. | |
| PLO13 | Yetkinlikler - Öğrenme Yetkinliği | Have the ability to design, develop, implement and improve integrated systems involving machine, time, information and money. | 4 |
| PLO14 | Yetkinlikler - Öğrenme Yetkinliği | Have the ability to design, develop, implement and improve complex products, processes, businesses, systems by applying modern design methods, under realistic conditions and constraints such as cost, environment, sustainability, manufacturability, ethical, health, safety and political issues. |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Python Basics | Resources given | Öğretim Yöntemleri: Anlatım, Alıştırma ve Uygulama |
| 2 | Numpy Library | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 3 | Pandas Library, Matplotlib Library | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 4 | Data preparation, cleaning and processing | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 5 | (Linear-Multiple-Polynomial Regression, Decision Tree Regression, Random Forest Regression) | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 6 | (K-Neirest Neighbour (KNN), Support Vector Machine (SVM), Naive Bayes, Decision Tree, Random Forest) | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 7 | Evaluation metrics and error functions | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 8 | Mid-Term Exam | Reading related resources and lecture notes | Ölçme Yöntemleri: Yazılı Sınav |
| 9 | Logistic Regression (Computation Graph, Initializing Parameters, Forward Propagation, Backward Propagation, Implementing Logistic Regression with Python, Implementing Logistic Regression with Sklearn) | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 10 | Backward Propagation, Implementing Logistic Regression with Python, Implementing Logistic Regression with Sklearn) | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 11 | Artificial Neural Network (Computation Graph, Initializing Parameters, Forward Propagation, Loss, Cost Function, Backward Propagation, Updata Parameters, Create Model, L-Layer Neural Network, L-Layer Neural Network with Keras) | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 12 | Artificial Neural Network 2 | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 13 | Artificial Neural Network 3 | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 14 | Convolutional Neural Network | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 15 | Convolotional Neural Network 2 | Reading related resources and lecture notes | Öğretim Yöntemleri: Anlatım |
| 16 | Term Exams | Reading related resources and lecture notes | Ölçme Yöntemleri: Yazılı Sınav |
| 17 | Term Exams | Reading related resources and lecture notes | Ölçme Yöntemleri: Yazılı Sınav |
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 | 3 | 42 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 0 | 0 | 0 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 7 | 7 |
| Final Exam | 1 | 18 | 18 |
| Total Workload (Hour) | 109 | ||
| Total Workload / 25 (h) | 4,36 | ||
| ECTS | 4 ECTS | ||