This course is an introduction to deep learning, a branch of machine learning concerned with the development and application of modern neural networks. We will cover a range of topics from basic neural networks, convolutional and recurrent network structures, deep unsupervised learning, and applications to problem domains like computer vision, image processing and natural language processing. The course will introduce training and optimization strategies in deep networks both for supervised and unsupervised learning tasks.
In this course, AI is a co-pilot. Following strategies will be used:
AI-Assisted Coding: Students are encouraged to use tools like GitHub Copilot or ChatGPT to boilerplate code, provided they can explain and document every line generated.
Socratic AI Tutoring: Using LLMs to simplify complex concepts (e.g., "Explain Backpropagation like I'm 5").
AI-Generated Synthetic Data: Using AI to create edge-case datasets for testing model robustness.
Red-Teaming AI: Critiquing AI-generated code for "hallucinations" or architectural inefficiencies.
Course Content
This course contains; Introduction to Machine Learning and Neural Networks,Training Neural Networks,Convolutional Neural Networks (CNNs),Network Layers in CNNs,Deep Learning Hardware and Software,Deep Network Architectures,Deep Learning Strategies,Recurrent Neural Networks and LSTMs,Natural Language Processing with Deep Learning,Computer Vision and Deep Learning,Image processing and Deep Learning,Unsupervised Learning and Generative Modeling,Advanced Applications of Deep Learning,Project Presentations.
Course Learning Outcomes
Teaching Methods
Assessment Methods
1. Design Convolutional Neural Networks for supervised and unsupervised learning, while using AI assistants to compare different architectural trade-offs.
12, 2, 21, 6, 9
A, E, F
2. Analyze the effects of hyper-parameters on learning performance using AI-driven simulation tools to visualize Loss Functions.
12, 2, 21, 6, 9
F
3. Apply advanced learning techniques for training deep networks and use LLMs to troubleshoot Gradient issues.
12, 2, 21, 6, 9
A, E, F
4. Implement applications of deep networks in computer vision, image processing, and natural language processing through AI-collaborative coding.
2, 21, 6, 9
E, F
5. Use current software and hardware tools for deep learning, including Generative AI platforms for code generation, documentation, and synthetic data augmentation.
2, 21, 6, 9
E, F
Teaching Methods:
12: Problem Solving Method, 2: Project Based Learning Model, 21: Simulation Technique, 6: Experiential Learning, 9: Lecture Method
Assessment Methods:
A: Traditional Written Exam, E: Homework, F: Project Task
Course Outline
Order
Subjects
Preliminary Work
1
Introduction to Machine Learning and Neural Networks
2
Training Neural Networks
3
Convolutional Neural Networks (CNNs)
4
Network Layers in CNNs
5
Deep Learning Hardware and Software
6
Deep Network Architectures
7
Deep Learning Strategies
8
Recurrent Neural Networks and LSTMs
9
Natural Language Processing with Deep Learning
10
Computer Vision and Deep Learning
11
Image processing and Deep Learning
12
Unsupervised Learning and Generative Modeling
13
Advanced Applications of Deep Learning
14
Project Presentations
Resources
Deep Learning, I. Goodfellow, Y. Bengio and A. Courville , MIT Press, http://www.deeplearningbook.org , 2016.
Machine Learning, Andrew Ng,Intel® AI Academy Deep Learning 501 https://software.intel.com/en-us/ai-academy/students/kits/deep-learning-501
Course Contribution to Program Qualifications
Course Contribution to Program Qualifications
No
Program Qualification
Contribution Level
1
2
3
4
5
1
Develop and deepen the current and advanced knowledge in the field with original thought and/or research and come up with innovative definitions based on Master's degree qualifications.
X
2
Conceive the interdisciplinary interaction which the field is related with ; come up with original solutions by using knowledge requiring proficiency on analysis, synthesis and assessment of new and complex ideas.
X
3
Evaluate and use new information within the field in a systematic approach and gain advanced level skills in the use of research methods in the field.
X
4
Develop an innovative knowledge, method, design and/or practice or adapt an already known knowledge, method, design and/or practice to another field.
X
5
Broaden the borders of the knowledge in the field by producing or interpreting an original work or publishing at least one scientific paper in the field in national and/or international refereed journals.
6
Contribute to the transition of the community to an information society and its sustainability process by introducing scientific, technological, social or cultural improvements.
7
Independently perceive, design, apply, finalize and conduct a novel research process.
X
8
Ability to communicate and discuss orally, in written and visually with peers by using a foreign language at least at a level of European Language Portfolio C1 General Level.
X
9
Critical analysis, synthesis and evaluation of new and complex ideas in the field.
X
10
Recognizes the scientific, technological, social or cultural improvements of the field and contribute to the solution finding process regarding social, scientific, cultural and ethical problems in the field and support the development of these values.
Assessment Methods
Contribution Level
Absolute Evaluation
Rate of Midterm Exam to Success
50
Rate of Final Exam to Success
50
Total
100
ECTS / Workload Table
Activities
Number of
Duration(Hour)
Total Workload(Hour)
Course Hours
14
3
42
Guided Problem Solving
0
0
0
Resolution of Homework Problems and Submission as a Report
5
20
100
Term Project
14
3
42
Presentation of Project / Seminar
1
20
20
Presentation of Project / Seminar
0
0
0
Quiz
0
0
0
Midterm Exam
0
0
0
General Exam
1
30
30
Performance Task, Maintenance Plan
0
0
0
Total Workload(Hour)
234
Dersin AKTS Kredisi = Toplam İş Yükü (Saat)/30*=(234/30)
8
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
CURRENT TOPICS in DEEP LEARNING
COED1212921
Spring Semester
3+0
3
8
Course Program
Çarşamba 12:00-12:45
Çarşamba 12:45-13:30
Çarşamba 13:30-14:15
Prerequisites Courses
Recommended Elective Courses
Language of Course
English
Course Level
Third Cycle (Doctorate Degree)
Course Type
Elective
Course Coordinator
Assist.Prof. Ahmet KAPLAN
Name of Lecturer(s)
Assist.Prof. Ahmet KAPLAN
Assistant(s)
Aim
This course is an introduction to deep learning, a branch of machine learning concerned with the development and application of modern neural networks. We will cover a range of topics from basic neural networks, convolutional and recurrent network structures, deep unsupervised learning, and applications to problem domains like computer vision, image processing and natural language processing. The course will introduce training and optimization strategies in deep networks both for supervised and unsupervised learning tasks.
In this course, AI is a co-pilot. Following strategies will be used:
AI-Assisted Coding: Students are encouraged to use tools like GitHub Copilot or ChatGPT to boilerplate code, provided they can explain and document every line generated.
Socratic AI Tutoring: Using LLMs to simplify complex concepts (e.g., "Explain Backpropagation like I'm 5").
AI-Generated Synthetic Data: Using AI to create edge-case datasets for testing model robustness.
Red-Teaming AI: Critiquing AI-generated code for "hallucinations" or architectural inefficiencies.
Course Content
This course contains; Introduction to Machine Learning and Neural Networks,Training Neural Networks,Convolutional Neural Networks (CNNs),Network Layers in CNNs,Deep Learning Hardware and Software,Deep Network Architectures,Deep Learning Strategies,Recurrent Neural Networks and LSTMs,Natural Language Processing with Deep Learning,Computer Vision and Deep Learning,Image processing and Deep Learning,Unsupervised Learning and Generative Modeling,Advanced Applications of Deep Learning,Project Presentations.
Course Learning Outcomes
Teaching Methods
Assessment Methods
1. Design Convolutional Neural Networks for supervised and unsupervised learning, while using AI assistants to compare different architectural trade-offs.
12, 2, 21, 6, 9
A, E, F
2. Analyze the effects of hyper-parameters on learning performance using AI-driven simulation tools to visualize Loss Functions.
12, 2, 21, 6, 9
F
3. Apply advanced learning techniques for training deep networks and use LLMs to troubleshoot Gradient issues.
12, 2, 21, 6, 9
A, E, F
4. Implement applications of deep networks in computer vision, image processing, and natural language processing through AI-collaborative coding.
2, 21, 6, 9
E, F
5. Use current software and hardware tools for deep learning, including Generative AI platforms for code generation, documentation, and synthetic data augmentation.
2, 21, 6, 9
E, F
Teaching Methods:
12: Problem Solving Method, 2: Project Based Learning Model, 21: Simulation Technique, 6: Experiential Learning, 9: Lecture Method
Assessment Methods:
A: Traditional Written Exam, E: Homework, F: Project Task
Course Outline
Order
Subjects
Preliminary Work
1
Introduction to Machine Learning and Neural Networks
2
Training Neural Networks
3
Convolutional Neural Networks (CNNs)
4
Network Layers in CNNs
5
Deep Learning Hardware and Software
6
Deep Network Architectures
7
Deep Learning Strategies
8
Recurrent Neural Networks and LSTMs
9
Natural Language Processing with Deep Learning
10
Computer Vision and Deep Learning
11
Image processing and Deep Learning
12
Unsupervised Learning and Generative Modeling
13
Advanced Applications of Deep Learning
14
Project Presentations
Resources
Deep Learning, I. Goodfellow, Y. Bengio and A. Courville , MIT Press, http://www.deeplearningbook.org , 2016.
Machine Learning, Andrew Ng,Intel® AI Academy Deep Learning 501 https://software.intel.com/en-us/ai-academy/students/kits/deep-learning-501
Course Contribution to Program Qualifications
Course Contribution to Program Qualifications
No
Program Qualification
Contribution Level
1
2
3
4
5
1
Develop and deepen the current and advanced knowledge in the field with original thought and/or research and come up with innovative definitions based on Master's degree qualifications.
X
2
Conceive the interdisciplinary interaction which the field is related with ; come up with original solutions by using knowledge requiring proficiency on analysis, synthesis and assessment of new and complex ideas.
X
3
Evaluate and use new information within the field in a systematic approach and gain advanced level skills in the use of research methods in the field.
X
4
Develop an innovative knowledge, method, design and/or practice or adapt an already known knowledge, method, design and/or practice to another field.
X
5
Broaden the borders of the knowledge in the field by producing or interpreting an original work or publishing at least one scientific paper in the field in national and/or international refereed journals.
6
Contribute to the transition of the community to an information society and its sustainability process by introducing scientific, technological, social or cultural improvements.
7
Independently perceive, design, apply, finalize and conduct a novel research process.
X
8
Ability to communicate and discuss orally, in written and visually with peers by using a foreign language at least at a level of European Language Portfolio C1 General Level.
X
9
Critical analysis, synthesis and evaluation of new and complex ideas in the field.
X
10
Recognizes the scientific, technological, social or cultural improvements of the field and contribute to the solution finding process regarding social, scientific, cultural and ethical problems in the field and support the development of these values.
