Course Objectives: |
Understanding the basics of deep learning, using open source libraries related to deep learning, developing deep learning applications.
|
Course Content: |
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
|
Week |
Subject |
Related Preparation |
1) |
Introduction, Artificial Intelligence, Machine Learning and Deep Learning |
none |
2) |
Mathematical background, tensor operations, activation functions |
none |
3) |
Gradient descent and variants, loss functions |
none |
4) |
Feedforward networks and training, Keras deep learning library |
none |
5) |
Data preprocessing, regularization methods |
none |
6) |
Convolutional neural networks (convnets) |
none |
7) |
Transfer learning |
none |
8) |
Text processing, embedding layers |
none |
9) |
Sequence processing, Recurrent neural networks (RNN) |
none |
10) |
Simple RNN,LSTM, GRU |
none |
11) |
Keras functional API |
none |
12) |
Generative deep learning |
none |
13) |
Contemporary deep learning topics |
none |
14) |
Presentations |
none |
|
Program Outcomes |
Level of Contribution |
1) |
Sufficient knowledge in mathematics, science and software engineering discipline-specific topics; the theoretical and practical knowledge in these areas, the ability to use in complex engineering problems. |
|
2) |
The ability to identify, formulate, and solve complex engineering problems; selecting and applying appropriate analysis and modelling methods for this purpose. |
|
3) |
The ability to design a complex system, process, device or product under realistic constraints and conditions to meet specific requirements; the ability to apply modern design methods for this purpose. |
|
4) |
Ability to develop, select and use modern techniques and tools necessary for analysis and solution of complex problems in engineering applications; ability to use information technologies effectively. |
|
5) |
Ability to design experiments, conduct experiments, collect data, analyse and interpret the results of complex engineering problems or discipline-specific research topics. |
|
6) |
Disiplin içi ve çok disiplinli takımlarda etkin biçimde çalışabilme becerisi; bireysel çalışma becerisi. |
|
7) |
Awareness of the need for lifelong learning; access to knowledge, ability to follow developments in science and technology, and constant self-renewal. |
|
8) |
Effective communication skills in Turkish oral and written communication; at least one foreign language knowledge; ability to write effective reports and understand written reports, to prepare design and production reports, to make effective presentations, to give clear and understandable instructions and to receive. |
|
9) |
Conformity to ethical principles, professional and ethical responsibility; Information on standards used in engineering applications. |
|
10) |
Information on practices in business, such as project management, risk management and change management; awareness about entrepreneurship, innovation; information on sustainable development. |
|
11) |
Information on the effects of engineering applications on health, environment, and safety in universal and social dimensions, and on the problems of the modern age in engineering; awareness of the legal consequences of engineering solutions. |
|
12) |
Adequate skills in the analysis, design, verification, evaluation, implementation, implementation, and maintenance of software systems |
|