Course Details

DEEP LEARNING IN PYTHON

Course Information

Semester	Course Unit Code	Course Unit Title	T+P+L	Credit	Number of ECTS Credits
1	ECE566	DEEP LEARNING IN PYTHON	3+0+0	3	7,5

Course Details

Language of Instruction	English
Level of Course Unit	Master's Degree
Department / Program	ELECTRICAL AND COMPUTER ENGINEERING
Type of Program	Formal Education
Type of Course Unit	Elective
Course Delivery Method	Face To Face
Objectives of the Course	Develop knowledge for the fundamentals of machine learning and neural networks Learn the techniques used for developing deep learning models Develop skills for implementing machine learning models using libraries of Python
Course Content	This course introduces deep learning using Keras library of Python programming language. It covers deep architectures for multi-layer perceptrons, convolutional neural networks, recurrent neural networks, and autoencoders. Students will get hands-on practical knowledge implementing deep learning models and applying them to various machine learning problems.
Course Methods and Techniques
Prerequisites and co-requisities	None
Course Coordinator	None
Name of Lecturers	Associate Prof.Dr. ZAFER AYDIN zafer.aydin@agu.edu.tr
Assistants	None
Work Placement(s)	No

Recommended or Required Reading

Resources	Data representations of neural networks (LO1, LO2) Anatomy of neural networks (LO1, LO2, LO3, LO4) Fundamentals of machine learning (LO1, LO2, LO3, LO4) Training deep neural networks (LO1, LO2, LO3, LO4) Convolutional networks (LO1, LO2, LO3, LO4) Recurrent networks (LO1, LO2, LO3, LO4) Advanced deep learning practices (LO1, LO2, LO3, LO4)

Planned Learning Activities and Teaching Methods

Activities are given in detail in the section of "Assessment Methods and Criteria" and "Workload Calculation"

Assessment Methods and Criteria

Veri yok

ECTS Allocated Based on Student Workload

Activities	Quantity	Duration	Total Work Load
Yazılı Sınav	1	3	3
Ev Ödevi	1	5	5
Sunum için Hazırlık	1	5	5
Proje	1	30	30
Kısa Sınav	1	1	1
Okuma	1	2	2
İnceleme	1	6	6
Yazılım Deneyimi	1	15	15
Yüz Yüze Ders	1	3	3
Final Sınavı	1	3	3
Total Work Load			Number of ECTS Credits 2,5 73

Course Learning Outcomes: Upon the successful completion of this course, students will be able to:

No	Learning Outcomes
1	Explain fundamental techniques of deep learning methods
2	Implement deep learning models using libraries of Python
3	Perform simulations and experiments to train, optimize and evaluate deep learning models on real data sets
4	Solve machine learning problems by applying the appropriate deep learning techniques and models

Weekly Detailed Course Contents

Week	Topics	Study Materials	Materials
1	Data representations of neural networks: tensors, tensor operations, gradient based optimization
2	Anatomy of neural networks: Keras library, codes for classification and regression examples
3	Fundamentals of machine learning: evaluating machine learning models
4	Training deep neural networks: activations, batch normalization, optimization
5	Training deep neural networks: regularization
6	Midterm exam 1
7	Deep learning for computer vision: introduction to convnets, training a convnet from scratch on a small dataset
8	Semester break
9	Deep learning for computer vision: using a pre-trained convnet, visualizing what convnets learn
10	Deep learning for computer vision: segmentation, object detection
11	Midterm exam 2
12	Deep learning for text and sequences: text data, word embeddings, recurrent neurons and layers
13	Deep learning for text and sequences: LSTM and GRU layers, LSTM example, advanced techniques, recurrent dropout, bidirectional RNNs
14	Deep learning for text and sequences: 1D convolution and sequence processing with convnets, combining CNNs and RNNs
15	Advanced deep learning practices: Keras functional API, models as layers, monitoring deep learning models, hyper-parameter optimization, model ensembling
16	Final exam

Contribution of Learning Outcomes to Programme Outcomes

Contribution: 1: Very Slight 2:Slight 3:Moderate 4:Significant 5:Very Significant

https://sis.agu.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=77830&lang=en