Yazdır

Ders Tanımı

Ders Kodu Yarıyıl T+U Saat Kredi AKTS
DEEP LEARNING AND CONVULUTIONAL NEURAL NETWORKS BSM 432 8 3 + 0 3 5
Ön Koşul Dersleri
Önerilen Seçmeli Dersler
Dersin Dili Türkçe
Dersin Seviyesi Lisans
Dersin Türü SECMELI
Dersin Koordinatörü Doç.Dr. DEVRİM AKGÜN
Dersi Verenler
Dersin Yardımcıları
Dersin Kategorisi Alanına Uygun Öğretim
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 foundations, tensor operations, Graident descent, backpropagation, Keras deeplearning library and examples of usage, Models of machine learning, Convolution neural networks (convnets), feature extraction with pre-trained convnet  , convnet visualization, deep learning with text data , recurrent neural networks, 1D convnets for array processing, Keras functional API, Keras functions, TensorBoard visualization tool, Generative deep learning, Contemporary issues

Dersin Öğrenme Çıktıları Öğretim Yöntemleri Ölçme Yöntemleri
1 - Good understanding of deep learnig 1 - 2 - 3 - 4 - A - C -
2 - using the convnet structure 1 - 2 - 3 - 4 - A - C - F -
3 - Using open source libraries for deep learning 1 - 2 - 3 - 4 - A - C - F -
4 - Developing deep learning application 1 - 2 - 3 - 4 - A - C - F -
Öğretim Yöntemleri: 1:Lecture 2:Question-Answer 3:Discussion 4:Drilland Practice
Ölçme Yöntemleri: A:Testing C:Homework F:Performance Task

Ders Akışı

Hafta Konular ÖnHazırlık
1 Indroduction to deep learning
2 Mathematical background, tensor operations
3 Graident descent, backpropagation, loss functions
4 Keras deep learning library, usage examples with Python
5 Machine learning fundamentals, data preprocessing, feature learning
6 Convolutional neural networks (convnets)
7 Using a pretrained convnet to do feature extraction, convnet visualization
8 Deep learning for text, recurrent neural networks
9 1D convnets for sequence processing
10 Keras fonksiyonel API, Keras callbacks
11 TensorBoard visualization tool
12 Generative deep learning
13 Generating images with variational autoencoders
14 Presentations about contemporary deep learning topics

Kaynaklar

Ders Notu

Weekly slides

Ders Kaynakları

Goodfellow, Ian, et al. Deep learning. Vol. 1. Cambridge: MIT press, 2016.

Chollet, Francois. Deep learning with python. Manning Publications Co., 2017.


Döküman Paylaşımı


Dersin Program Çıktılarına Katkısı

No Program Öğrenme Çıktıları KatkıDüzeyi
1 2 3 4 5
1 To have sufficient foundations on engineering subjects such as science and discrete mathematics, probability/statistics; an ability to use theoretical and applied knowledge of these subjects together for engineering solutions, X
2 An ability to determine, describe, formulate and solve engineering problems; for this purpose, an ability to select and apply proper analytic and modeling methods,al background in describing, formulating, modeling and analyzing the engineering problem, with a consideration for appropriate analytical solutions in all necessary situations X
3 An ability to select and use modern techniques and tools for engineering applications; an ability to use information technologies efficiently, X
4 An ability to analyze a system, a component or a process and design a system under real limits to meet desired needs; in this direction, an ability to apply modern design methods, X
5 An ability to design, conduct experiment, collect data, analyze and comment on the results and consciousness of becoming a volunteer on research, X
6 Understanding, awareness of administration, control, development and security/reliability issues about information technologies, X
7 An ability to work efficiently in multidisciplinary teams, self confidence to take responsibility, X
8 An ability to present himself/herself or a problem with oral/written techniques and have efficient communication skills; know at least one extra language, X
9 An awareness about importance of lifelong learning; an ability to update his/her knowledge continuously by means of following advances in science and technology, X
10 Understanding, practicing of professional and ethical responsibilities, an ability to disseminate this responsibility on society,
11 An understanding of project management, workplace applications, health issues of laborers, environment and job safety; an awareness about legal consequences of engineering applications,
12 An understanding universal and local effects of engineering solutions; awareness of entrepreneurial and innovation and to have knowledge about contemporary problems.

Değerlendirme Sistemi

YARIYIL İÇİ ÇALIŞMALARI SIRA KATKI YÜZDESİ
AraSinav 1 50
KisaSinav 1 10
KisaSinav 2 10
ProjeTasarim 1 20
KisaSinav 3 10
Toplam 100
Yıliçinin Başarıya Oranı 50
Finalin Başarıya Oranı 50
Toplam 100

AKTS - İş Yükü

; ;