CS498 Special Topics in Computer Science I

Syllabus | International University of Sarajevo - Last Update on Oct 10, 2025

Referencing Curricula

HOSTED BY

Computer Sciences and Engineering

Academic Year

2025 - 2026

Semester

Fall

Course Code

CS498

Weekly Hours

3 Teaching + 2 Practice

ECTS

Prerequisites

None

Teaching Mode Delivery

Face-to-face

Prerequisite For

Teaching Mode Delivery Notes

Cycle

I Cycle

TBA

Course Lecturer

Position

tba@ius.edu.ba

Phone

033 957 -

Assistant(s)

Assistant E-mail

Course Objectives

The course introduces the fundamental differences between generative and discriminative models, explaining key probabilistic concepts essential for generative modeling. Students learn how deep learning enables working with unstructured data and how multilayer perceptrons (MLPs) are used for image classification. The architecture of convolutional neural networks (CNNs) is explained, highlighting their ability to capture spatial structure in images through convolutional layers. The course covers autoencoders in detail, focusing on their architecture and how they compress and reconstruct data via a latent space. The limitations of standard autoencoders in generating new data are discussed, leading to the introduction of variational autoencoders (VAEs). Students learn how VAEs use a probabilistic approach and KL divergence to better structure the latent space. The course demonstrates how VAEs can be used to generate new images, manipulate the latent space, and perform arithmetic on image features. Generative adversarial networks (GANs) are introduced, with an explanation of their architecture and the challenges in training generators and discriminators. Special attention is given to advanced GAN architectures such as DCGAN and WGAN-GP, which enable more stable and higher-quality image generation. Through practical examples and Keras implementations, students gain the knowledge and skills to build, train, and evaluate generative models. Students will be introduced to the challenges of developing GenAI solutions and will have the opportunity to gain insights into real-world applications and industry use cases of generative AI.

Learning Outcomes

After successful completion of the course, the student will be able to:

Understand emerging trends and cutting-edge developments in computer science and related interdisciplinary areas.

Demonstrate comprehension of advanced concepts presented in the selected current topic of the course.

Apply suitable methods and tools to analyze, design, and implement solutions relevant to the selected topic.

Critically evaluate the obtained results.

Present the results effectively in oral or written form.

Course Materials

Required Textbook

David Foster, “Generative Deep Learning, 2nd Edition”, 2023.

Additional Literature

Tom Taulli, „Generative AI: How ChatGPT and Other AI Tools Will Revolutionize Business“, 2023.

Teaching Methods

Weekly Topics

This weekly planning is subject to change with advance notice.

Week	Topic	Readings / References
1	Introduction: Introduction to generative modeling, course overview, real-world applications, and business relevance.
2	Fundamentals of Generative Modeling: Key differences between generative and discriminative models, probabilistic foundations, and model families.
3	Multilayer Perceptron (MLP): Deep learning basics, unstructured data, and building MLPs for image classification.
4	Convolutional Neural Networks (CNN): CNN architecture, spatial structure in images, and regularization techniques.
5	Autoencoders: Autoencoder architecture, latent space visualization, and generative capabilities.
6	Variational Autoencoder (VAE) – Introduction: Probabilistic encoding, KL divergence, and building a basic VAE.
7	Variational Autoencoder (VAE) – Exploring the Latent Space: Training VAEs on complex datasets, latent space arithmetic, and image manipulation.
8	Midtearm exam
9	Generative Adversarial Networks (GAN) – DCGAN: GAN fundamentals, DCGAN architecture, and challenges in GAN training.
10	WGAN-GP: Wasserstein loss, gradient penalty, and building stable WGAN-GP models.
11	CGAN: Introduction to Conditional GANs (CGAN), conditioning generative models on labels or attributes, and practical applications of CGANs.
12	GenAI business applications: Innovative solutions with GenAI, startup ecosystem, business perspective, and real-world case studies.
13	Real-world applications and industry insights: Practical challenges in developing GenAI solutions, strategies to overcome them, and lessons from industry practice.
14	Research and Presentations – Comparative Analysis: Comprehensive overview of architectures, parameter impact evaluation, comparisons, and application insights.
15	Final Presentations and Concluding Discussions: Presenting final results, synthesizing conclusions, and exploring future directions.

Course Schedule (All Sections)

Section	Type	Day 1	Venue 1	Day 2	Venue 2
CS498.1	Course	Monday 17:00 - 19:50	B F1.8	-	-

Office Hours & Room

Course Office hours will be available here soon.

Assessment Methods and Criteria

Assessment Components

30%x1

Final Exam / Final Project

AI: Not Allowed

Alignment with Learning Outcomes : 3

30%x1

Midterm

AI: Not Allowed

Alignment with Learning Outcomes : 1 5

20%x1

Project assignment and presentation

AI: Not Allowed

Alignment with Learning Outcomes : 2 4

20%x2

Quizzes

AI: Not Allowed

Alignment with Learning Outcomes : 3

IUS Grading System

Grading Scale	IUS Grading System	IUS Coeff.	Letter (B&H)	Numerical (B&H)
0 - 44	F	0	F	5
45 - 54	E	1	F	5
55 - 64	C	2	E	6
65 - 69	C+	2.3	D	7
70 -74	B-	2.7	D	7
75 - 79	B	3	C	8
80 - 84	B+	3.3	C	8
85 - 94	A-	3.7	B	9
95 - 100	A	4	A	10

Late Work Policy

Information about late submission policies will be shared during class and posted in this section. Please check back for official guidelines.

ECTS Credit Calculation

📚 Student Workload

This 6 ECTS credit course corresponds to 150 hours of total student workload, distributed as follows:

Lecture Hours

45 hours ⏳ (15 week × 3 h)

Home Study

84 hours ⏳ (14 week × 6 h)

In-term Exam Study

8 hours ⏳ (1 week × 8 h)

Final Exam Study

13 hours ⏳ (1 week × 13 h)

150 Total Workload Hours

6 ECTS Credits

Course Policies

Academic Integrity

All work submitted must be your own. Plagiarism, cheating, or any form of academic dishonesty will result in disciplinary action according to university policies. When in doubt about citation practices, consult the instructor.

Attendance Policy

Students are expected to adhere to the attendance requirements as outlined in the International University of Sarajevo Study Rules and Regulations. Excessive absences, whether excused or unexcused, may impact academic performance and eligibility for assessment. Mandatory sessions (e.g., labs, workshops) require attendance unless formally exempted. For detailed policies on absences, documentation, and penalties, please refer to the official university regulations.

Technology & AI Policy

Laptops/tablets may be used for note-taking only during lectures. Phones should be silenced and put away during all class sessions. Audio/video recording requires prior permission from the instructor.

Artificial Intelligence (AI) Usage: The use of AI tools (e.g., ChatGPT, Copilot, Gemini) varies by assessment component. Please refer to the AI usage indicator next to each assessment item in the Assessment Methods and Criteria section above. Submitting AI-generated content as your own work, where AI is not explicitly allowed, constitutes an academic integrity violation.

Communication Policy

All course-related communication should occur through official university channels (institutional email or SIS). Emails should include [CS498] in the subject line.

Academic Quality Assurance Policy

Course Academic Quality Assurance is achieved through Semester Student Survey. At the end of each academic year, the institution of higher education is obliged to evaluate work of the academic staff, or the success of realization of the curricula.

More info

Learning Tips

Engage Actively

Be prepared to contribute thoughtfully during class discussions, labs, or collaborative work. Active participation deepens understanding and encourages critical thinking.

Read and Review Purposefully

Complete assigned readings or prep materials before class. Take notes, highlight key ideas, and jot down questions. Aim to grasp core concepts and their applications—not just facts.

Think Critically in Assignments

Use course frameworks or methodologies to analyze problems, case studies, or projects. Begin early to allow time for reflection and refinement. Seek feedback to improve your work.

Ask Questions Early

Don’t hesitate to reach out when something is unclear. Use office hours, discussion boards, or peer networks to clarify concepts and stay on track.

Syllabus Last Updated on Oct 10, 2025 | International University of Sarajevo

Print Syllabus

Referencing Curricula Print this page

Course Code	Course Title			Weekly Hours*		ECTS		Weekly Class Schedule
				T	P
CS498	Special Topics in Computer Science I			3	2	6
Prerequisite	None		It is a prerequisite to	-
Lecturer	TBA		Office Hours / Room / Phone
E-mail	TBA
Assistant			Assistant E-mail
Course Objectives	The course introduces the fundamental differences between generative and discriminative models, explaining key probabilistic concepts essential for generative modeling. Students learn how deep learning enables working with unstructured data and how multilayer perceptrons (MLPs) are used for image classification. The architecture of convolutional neural networks (CNNs) is explained, highlighting their ability to capture spatial structure in images through convolutional layers. The course covers autoencoders in detail, focusing on their architecture and how they compress and reconstruct data via a latent space. The limitations of standard autoencoders in generating new data are discussed, leading to the introduction of variational autoencoders (VAEs). Students learn how VAEs use a probabilistic approach and KL divergence to better structure the latent space. The course demonstrates how VAEs can be used to generate new images, manipulate the latent space, and perform arithmetic on image features. Generative adversarial networks (GANs) are introduced, with an explanation of their architecture and the challenges in training generators and discriminators. Special attention is given to advanced GAN architectures such as DCGAN and WGAN-GP, which enable more stable and higher-quality image generation. Through practical examples and Keras implementations, students gain the knowledge and skills to build, train, and evaluate generative models. Students will be introduced to the challenges of developing GenAI solutions and will have the opportunity to gain insights into real-world applications and industry use cases of generative AI.
Textbook	David Foster, “Generative Deep Learning, 2nd Edition”, 2023.
Additional Literature	Tom Taulli, „Generative AI: How ChatGPT and Other AI Tools Will Revolutionize Business“, 2023.
Learning Outcomes	After successful completion of the course, the student will be able to:
	Understand emerging trends and cutting-edge developments in computer science and related interdisciplinary areas. Demonstrate comprehension of advanced concepts presented in the selected current topic of the course. Apply suitable methods and tools to analyze, design, and implement solutions relevant to the selected topic. Critically evaluate the obtained results. Present the results effectively in oral or written form.
Teaching Methods
Teaching Method Delivery	Face-to-face	Teaching Method Delivery Notes
WEEK	TOPIC						REFERENCE
Week 1	Introduction: Introduction to generative modeling, course overview, real-world applications, and business relevance.
Week 2	Fundamentals of Generative Modeling: Key differences between generative and discriminative models, probabilistic foundations, and model families.
Week 3	Multilayer Perceptron (MLP): Deep learning basics, unstructured data, and building MLPs for image classification.
Week 4	Convolutional Neural Networks (CNN): CNN architecture, spatial structure in images, and regularization techniques.
Week 5	Autoencoders: Autoencoder architecture, latent space visualization, and generative capabilities.
Week 6	Variational Autoencoder (VAE) – Introduction: Probabilistic encoding, KL divergence, and building a basic VAE.
Week 7	Variational Autoencoder (VAE) – Exploring the Latent Space: Training VAEs on complex datasets, latent space arithmetic, and image manipulation.
Week 8	Midtearm exam
Week 9	Generative Adversarial Networks (GAN) – DCGAN: GAN fundamentals, DCGAN architecture, and challenges in GAN training.
Week 10	WGAN-GP: Wasserstein loss, gradient penalty, and building stable WGAN-GP models.
Week 11	CGAN: Introduction to Conditional GANs (CGAN), conditioning generative models on labels or attributes, and practical applications of CGANs.
Week 12	GenAI business applications: Innovative solutions with GenAI, startup ecosystem, business perspective, and real-world case studies.
Week 13	Real-world applications and industry insights: Practical challenges in developing GenAI solutions, strategies to overcome them, and lessons from industry practice.
Week 14	Research and Presentations – Comparative Analysis: Comprehensive overview of architectures, parameter impact evaluation, comparisons, and application insights.
Week 15	Final Presentations and Concluding Discussions: Presenting final results, synthesizing conclusions, and exploring future directions.

Assessment Methods and Criteria	Evaluation Tool	Quantity	Weight	Alignment with LOs	AI Usage
	Final Exam / Final Project	1	30	3	Not Allowed
	Semester Evaluation Components
	Midterm	1	30	1,5	Not Allowed
	Project assignment and presentation	1	20	2,4	Not Allowed
	Quizzes	2	20	3	Not Allowed
* ECTS Credit Calculation *

Activity	Hours	Weeks	Student Workload Hours	Activity	Hours	Weeks	Student Workload Hours
Lecture Hours	3	15	45				0
Home Study	6	14	84	In-term Exam Study	8	1	8
Final Exam Study	13	1	13
				Total Workload Hours =			150
*T= Teaching, P= Practice				ECTS Credit =			6
Course Academic Quality Assurance: Semester Student Survey						Last Update Date: 31/10/2025

Print this page

CS498 Special Topics in Computer Science I

Computer Sciences and Engineering

TBA

Course Objectives

Learning Outcomes

Course Materials

Required Textbook

Additional Literature

Teaching Methods

Weekly Topics Expand All

Course Schedule (All Sections)

Office Hours & Room

Assessment Methods and Criteria

Assessment Components

Final Exam / Final Project

Midterm

Project assignment and presentation

Quizzes

IUS Grading System

Late Work Policy

ECTS Credit Calculation

📚 Student Workload

Lecture Hours

Home Study

In-term Exam Study

Final Exam Study

Course Policies

Academic Integrity

Attendance Policy

Technology & AI Policy

Communication Policy

Academic Quality Assurance Policy

Learning Tips

Weekly Topics