Course Information
SemesterCourse Unit CodeCourse Unit TitleT+P+LCreditNumber of ECTS CreditsLast Updated Date
1AIN422Deep Learning Laboratory0+2+01412.08.2025

 
Course Details
Language of Instruction English
Level of Course Unit Bachelor's Degree
Department / Program ARTIFICIAL INTELLIGENCE ENGINEERING
Type of Program Formal Education
Type of Course Unit Elective
Course Delivery Method Face To Face
Objectives of the Course To help students gain pratical skills on fundamental applications of deep learning.
Course Content Neural networks, learning in neural networks, backpropagation,supervised deep learning techniques, convolutional neural networks, unsupervised deep learning methods, recurrent neural networks, foundations of deep reinforcement learning, modelling sequential data, foundations of deep generative adversarial networks.
Course Methods and Techniques Lecture, Drill and Practice, Problem Solving, Preparing and/or Presenting Reports
Prerequisites and co-requisities ( BBM102 ) and ( BBM104 ) and ( AIN420 )
Course Coordinator None
Name of Lecturers Asist Prof.Dr. Cemil Zalluhoğlu
Assistants None
Work Placement(s) No

Recommended or Required Reading
Resources Ian Goodfellow, Yoshua Bengio, Aaron Courville "Deep Learning" MIT Press, 2016. Michael Nielsen, ?Neural Networks and Deep Learning?, Online Book, 2016
Course Notes Ian Goodfellow, Yoshua Bengio, Aaron Courville "Deep Learning" MIT Press, 2016.

Michael Nielsen, “Neural Networks and Deep Learning”, Online Book, 2016


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
In-Term Studies Quantity Percentage
Midterm Exam 4 % 20
Assignment 2 % 50
Final examination 1 % 30
Total
7
% 100

 
ECTS Allocated Based on Student Workload
Activities Quantity Duration Total Work Load
Course Duration 14 2 28
Hours for off-the-c.r.stud 7 1 7
Assignments 2 25 50
Preparation for Midterm Exam 4 2,5 10
General Exam Preparation 1 25 25
Total Work Load   Number of ECTS Credits 4 120

 
Course Learning Outcomes: Upon the successful completion of this course, students will be able to:
NoLearning Outcomes
1 In completition of this course, the student will,
2 1- Gain practical knowledge on developing deep learning applications. ms.
3 2- Improve the problem analysis and solving skills on deep learning.
4 3- Be able to conduct initial research and produce reports on the subject.
5 4- Implement deep learning algorithms in various platfor
6  
7  
8  

 
Weekly Detailed Course Contents
WeekTopicsStudy MaterialsMaterials
1 Introduction
2 Neural Networks and Learning in NNs
3 Neural Networks and Learning in NNs
4 Convolutional Neural Networks
5 Convolutional Neural Networks
6 Recurrent neural networks and modelling sequence data
7 Long short term memory and GRU models
8 Midterm
9 Attention models
10 Autoencoders and unsupervised deep learning
11 Representation learning
12 Deep Generative Adversarial Networks
13 Foundations of Deep Reinforcement Learning
14 Applications of deep learning
15 Final exam preparation
16 Final exam

 
Contribution of Learning Outcomes to Programme Outcomes
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12
All 5 4 3 4 5 3 3 4 2 2 2 4
C1
C2
C3
C4
C5
C6
C7
C8

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

  
  https://bilsis.hacettepe.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=2733689&lang=en