Ders Adı | Kodu | Yarıyıl | T+U Saat | Kredi | AKTS |
---|---|---|---|---|---|
Deep Learning | BSM 558 | 0 | 3 + 0 | 3 | 6 |
Ön Koşul Dersleri | |
Önerilen Seçmeli Dersler | |
Dersin Dili | İngilizce |
Dersin Seviyesi | YUKSEK_LISANS |
Dersin Türü | Seçmeli |
Dersin Koordinatörü | Prof.Dr. DEVRİM AKGÜN |
Dersi Verenler | Prof.Dr. DEVRİM AKGÜN, |
Dersin Yardımcıları | |
Dersin Kategorisi | Diğer |
Dersin Amacı | To teach mathematical fundamentals about deep learning, to use open source libraries related to deep learning, to develop deep learning applications. |
Dersin İçeriği | Mathematical background, tensor operations, Graident descent, backpropagation, Keras deeplearning library , Machine learning models, Convolutional neural networks (convnets), transfer learning ,metin verileriyle derin öğrenme, recurrent neural networks, 1D convnets , Keras functional API, Generative deep learning, current topics |
# | Ders Öğrenme Çıktıları | Öğretim Yöntemleri | Ölçme Yöntemleri |
---|---|---|---|
1 | To understand deep learning basics | Lecture, Question-Answer, Project Based Learning, | Testing, Homework, Project / Design, |
2 | To understand neural network types | Problem Solving, Lecture, | Project / Design, Homework, Testing, |
3 | To design, train and test deep learning models | Lecture, | Project / Design, Homework, Testing, |
Hafta | Ders Konuları | Ön Hazırlık |
---|---|---|
1 | Introduction, Artificial Intelligence, Machine Learning and Deep Learning | |
2 | Mathematical background, tensor operations, activation functions | |
3 | Gradient descent and variants, loss functions | |
4 | Feedforward networks and training, Keras deep learning library | |
5 | Data preprocessing, regularization methods | |
6 | Convolutional neural networks (convnets) | |
7 | Transfer learning | |
8 | Text processing, embedding layers | |
9 | Sequence processing, Recurrent neural networks (RNN) | |
10 | Simple RNN,LSTM, GRU | |
11 | Keras functional API | |
12 | Generative deep learning | |
13 | Contemporary deep learning topics | |
14 | Presentations |
Kaynaklar | |
---|---|
Ders Notu | |
Ders Kaynakları | Chollet, Francois. Deep learning with python. Manning Publications Co., 2017. Ders Kaynakları Goodfellow, Ian, et al. Deep learning. Vol. 1. Cambridge: MIT press, 2016.
|
Sıra | Program Çıktıları | Katkı Düzeyi | |||||
---|---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | 5 | |||
1 | ability to access wide and deep information with scientific researches in the field of Engineering, evaluate, interpret and implement the knowledge gained in his/her field of study | X | |||||
2 | ability to complete and implement “limited or incomplete data” by using the scientific methods. | X | |||||
3 | ability to consolidate engineering problems, develop proper method(s) to solve and apply the innovative solutions to them | X | |||||
4 | ability to develop new and original ideas and method(s), to develop new innovative solutions at design of system, component or process | X | |||||
5 | gain comprehensive information on modern techniques, methods and their borders which are being applied to engineering | X | |||||
6 | ability to design and apply analytical, modelling and experimental based research, analyze and interpret the faced complex issues during the design and apply process | X | |||||
7 | gain high level ability to define the required information and data | X | |||||
8 | ability to work in multi-disciplinary teams and to take responsibility to define approaches for complex situations | X | |||||
9 | systematic and clear verbal or written transfer of the process and results of studies at national and international environments | ||||||
10 | aware of social, scientific and ethical values guarding adequacy at all professional activities and at the stage of data collection, interpretation and announcement | ||||||
11 | aware of new and developing application of profession and ability to analyze and study on those applications | X | |||||
12 | ability to interpret engineering application’s social and environmental dimensions and it’s compliance with the social environment |
Değerlendirme Sistemi | |
---|---|
Yarıyıl Çalışmaları | Katkı Oranı |
1. Ara Sınav | 40 |
1. Ödev | 10 |
2. Ödev | 10 |
1. Proje / Tasarım | 40 |
Toplam | 100 |
1. Yıl İçinin Başarıya | 50 |
1. Final | 50 |
Toplam | 100 |
AKTS - İş Yükü Etkinlik | Sayı | Süre (Saat) | Toplam İş Yükü (Saat) |
---|---|---|---|
Assignment | 2 | 12 | 24 |
Mid-terms | 1 | 12 | 12 |
Project / Design | 1 | 12 | 12 |
Final examination | 1 | 15 | 15 |
Course Duration (Including the exam week: 16x Total course hours) | 14 | 3 | 42 |
Hours for off-the-classroom study (Pre-study, practice) | 14 | 3 | 42 |
Toplam İş Yükü | 147 | ||
Toplam İş Yükü / 25 (Saat) | 5,88 | ||
Dersin AKTS Kredisi | 6 |