1. Education Information System
  2. Information Systems Engineering
  3. Introduction To Deep Learning (2020 - 2021)
Course Name Code Semester T+U Hours Credit ECTS
Introduction To Deep Learning ISE 469 7 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

Introduction to Artificial incelligence, machine learning and deep learning. Mathematical background. Gradient Descent algorithms, loss functions, backpropogation. Keras deep learning library,  tensor operations in Python.  Multi label classification, Regression. Data prepocessig, overfitting, weight regularization, dropout. 2D Convolution (conv2D) neural networks (convnets), pooling. Image data augmentation. Pretrained networks, fine tuning Visualizing convnet filters. Deep learning with text data. Emedding layers. Recurrent neural networks, LSTM and GRU layers. 1D convnets for sequence data.  Keras functional API,  Multi input multi output models. Generative deep learning.  Presentations about state of the art topics.
# Course Learning Outcomes Teaching Methods Assessment Methods
1 Knows the basic topics about deep learning Lecture, Question-Answer, Drilland Practice, Problem Solving, Project Based Learning, Testing, Homework, Project / Design, Performance Task,
2 Knows 1D and 2D convnet-convolution layers. Lecture, Question-Answer, Drilland Practice, Problem Solving, Project Based Learning, Testing, Homework, Project / Design, Performance Task,
3 Uses open source libraries for deep learning Lecture, Question-Answer, Drilland Practice, Problem Solving, Project Based Learning, Testing, Homework, Project / Design, Performance Task,
4 Knows text processing, Embedding Layer, Simple RNN, LTSM and GRU layers Lecture, Question-Answer, Drilland Practice, Problem Solving, Project Based Learning, Testing, Homework, Project / Design, Performance Task,
Week Course Topics Preliminary Preparation
1 Overview of artificial intelligence, machine learning and deep learning Slides
2 Mathematical foundations, Gradient descent algorithms, loss functions, backpropagation. Slides
3 Tensor operations with Python, Keras deep learning library Slides
4 Multi-label classification, Regression Slides
5 Data preprocessing, overfitting prevention, weight regularization, dropout Slides
6 2-Dimensional Convolution (conv2D) Neural Networks (convnets), pooling Slides
7 Augmentation of image data, pretrained networks Slides
8 Fine tuning, convolution filters visualization Slides
9 Deep learning with text data, Embedding layers Slides
10 Recurrent neural networks, LSTM and GRU layers Slides
11 Array processing with 1D convnets Slides
12 Keras functional API, Multiple input or multiple output models Slides
13 Generative deep learning Slides
14 Presentations on state of the art topics in deep learning Slides
Resources
Course Notes <p>Weekly uploaded slides</p>
Course Resources

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

Goodfellow, Ian, et al. Deep learning. Vol. 1. Cambridge: MIT press, 2016.
Order Program Outcomes Level of Contribution
1 2 3 4 5
1 X
2 X
3 X
4 X
5 X
6
7 X
8
9 X
10
11
12
Evaluation System
Semester Studies Contribution Rate
1. Ara Sınav 60
1. Ödev 10
2. Ödev 10
1. Proje / Tasarım 20
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
Quiz 1 6 6
Performance Task (Application) 2 7 14
Final examination 1 15 15
Total Workload 125
Total Workload / 25 (Hours) 5
dersAKTSKredisi 5