Deep Learning
| Title | Βαθιά Μάθηση / Deep Learning |
| Code | 133 |
| Faculty | Engineering |
| School | Electrical and Computer Engineering |
| Cycle / Level | 1st / Undergraduate |
| Teaching Period | Winter/Spring |
| Coordinator | Panagiotis Petrantonakis |
| Common | No |
| Status | Active |
| Course ID | 600026756 |
Programme of Study: Electrical and Computer Engineering
Registered students: 76
| Orientation | Attendance Type | Semester | Year | ECTS |
|---|---|---|---|---|
| ELECTRICAL ENERGY | Elective Courses | 9 | 5 | 5 |
| ELECTRONICS AND COMPUTER ENGINEERING | Elective Courses | 9 | 5 | 5 |
| TELECOMMUNICATIONS | Elective Courses | 9 | 5 | 5 |
| Academic Year | 2025 – 2026 |
| Class Period | Winter |
| Faculty Instructors | |
| Weekly Hours | 4 |
| Class ID | 600287486
|
Course Type 2021
Specialization / Direction
Mode of Delivery
- Face to face
Digital Course Content
- e-Study Guide https://qa.auth.gr/en/class/1/600287486
Language of Instruction
- Greek (Instruction, Examination)
Learning Outcomes
By the end of the course students are expected to:
a) Know the basic principles of deep learning theory and understand the fundamental deep learning methods and algorithms
c) Apply well-known algorithms to pilot problems
d) Select the most efficient algorithm based on problem requirements and implement it in suitable software packages.
e) Design the methodology for deep learning problems of medium complexity
General Competences
- Apply knowledge in practice
- Make decisions
- Work in teams
Course Content (Syllabus)
Review of basic machine learning and computational intelligence concepts. Neural Network models and architectures, learning algorithms. Perceptron, multilayer perceptron. Deep feedforward neural networks. Loss functions, activation functions, optimization. Regularization. Convolutional Neural Networks and variations. Sequence models. Recurrent Neural Networks (RNN) and variations. Attention, self-attention, multi-head attention. Transformers. Autoencoders.
Keywords
Deep Learning, Neural Networks
Educational Material Types
- Slide presentations
- Book
- Projects
Use of Information and Communication Technologies
Use of ICT
- Use of ICT in Course Teaching
Course Organization
| Activities | Workload | ECTS | Individual | Teamwork | Erasmus |
|---|---|---|---|---|---|
| Lectures | 39 | 1.3 | ✓ | ||
| Reading Assigment | 16 | 0.5 | ✓ | ||
| Tutorial | 27 | 0.9 | ✓ | ||
| Written assigments | 44 | 1.5 | ✓ | ||
| Exams | 24 | 0.8 | ✓ | ||
| Total | 150 | 5 |
Student Assessment
Student Assessment methods
- Written Exam with Multiple Choice Questions (Formative)
- Written Exam with Short Answer Questions (Formative)
- Written Exam with Extended Answer Questions (Formative)
- Written Assignment (Summative)
- Oral Exams (Formative)
- Written Exam with Problem Solving (Formative)
- Report (Formative)
Bibliography
Course Bibliography (Eudoxus)
Τίτλος Συγγράμματος: «Βαθιά Μάθηση», Συγγραφείς: IAN GOODFELLOW, YOSHUA BENGIO, AARON COURVILLE, Εκδόσεις: 2024 ΚΛΕΙΔΑΡΙΘΜΟΣ
Κωδικός Βιβλίου στον Εύδοξο: 122075017 ΕΠΕ
Additional bibliography for study
Deep Learning – Foundations and Concepts, C. M. Bishop, H. Bishop, Springer, 2023
Last Update
04-09-2025
