Course Name Code Semester T+U Hours Credit ECTS
Deep Learning and Convulutional Neural Networks BSM 432 8 3 + 0 3 5
Precondition Courses
Recommended Optional Courses
Course Language Turkish
Course Level Bachelor's Degree
Course Type Optional
Course Coordinator Doç.Dr. DEVRİM AKGÜN
Course Lecturers Doç.Dr. DEVRİM AKGÜN,
Course Assistants
Course Category Field Proper Education
Course Objective

To teach mathematical fundamentals about deep learning, to use open source libraries related to deep learning, to develop deep learning applications.

Course Content

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

# Course Learning Outcomes Teaching Methods Assessment Methods
1 Good understanding of deep learnig Lecture, Question-Answer, Discussion, Drilland Practice, Testing, Homework,
2 Knows the network structures used in deep learning Drilland Practice, Discussion, Question-Answer, Lecture, Homework, Testing, Performance Task,
3 Develops applications with open source libraries about deep learning Drilland Practice, Discussion, Question-Answer, Lecture, Performance Task, Homework, Testing,
Week Course Topics Preliminary Preparation
1 Indroduction to deep learning, Mathematical background, tensor operations
2 Graident descent, backpropagation, loss functions
3 Keras deep learning library, usage examples with Python
4 Machine learning fundamentals
5 Data preprocessing, overfitting
6 Convolutional neural networks (convnets)
7 Pretrained convnets, transfer learning
8 Deep learning for text, Embedding layers
9 Recurrent neural networks, LSTM and GRU
10 1D convnets for sequence processing
11 Keras fonksiyonel API, Keras callbacks
12 Generative deep learning
13 Contemporary topics
14 Presentations
Resources
Course Notes <p> Weekly slides</p>
Course Resources

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

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

Order Program Outcomes Level of Contribution
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.
Evaluation System
Semester Studies Contribution Rate
1. Proje / Tasarım 20
1. Ara Sınav 50
1. Ödev 15
2. Ödev 15
Total 100
1. Final 50
1. Yıl İçinin Başarıya 50
Total 100
ECTS - Workload Activity Quantity Time (Hours) Total Workload (Hours)
Course Duration (Including the exam week: 16x Total course hours) 16 3 48
Hours for off-the-classroom study (Pre-study, practice) 16 2 32
Mid-terms 1 10 10
Assignment 2 5 10
Final examination 1 15 15
Project / Design 1 10 10
Total Workload 125
Total Workload / 25 (Hours) 5
dersAKTSKredisi 5