Cukurova University, Department of Computer Engineering, Balcali campus

Posts by Collection

portfolio

publications

Paper Title Number 4

Published in GitHub Journal of Bugs, 2024

This paper is about fixing template issue #693.

Recommended citation: Your Name, You. (2024). "Paper Title Number 3." GitHub Journal of Bugs. 1(3).
Download Paper

talks

teaching

Advanced Machine Learning

MSc Course, CuCEng, 2025

Course Description

This Master’s level course dives deep into the theoretical and practical foundations of modern machine learning, focusing primarily on Deep Learning (DL) architectures, advanced optimization techniques, and probabilistic models. The course adopts a seminar and project-based structure, requiring students to engage critically with seminal papers and implement sophisticated models.

Computational Linguistics

MSc Course, CuCEng, 2025

Course Objective

Theoretical foundations of modern language models, deep linguistic analysis, and LLM architectures. Unlike standard NLP engineering courses, this course focuses on the “Why” and “How” of linguistic theories as applied to deep learning architectures, moving from sub-word morphology to the latest large language model alignment techniques.

Discrete Mathematics

Undergraduate Course, CuCEng, 2025

Course Objectives

This course introduces the mathematical foundations of computer science, covering topics such as formal logic, set theory, mathematical induction, methods of counting, discrete probability, and elementary graph theory.

Graph Theory

PhD Course, CuCEng, 2025

Course Description

This course is designed for PhD students to explore the mathematical foundations of graph theory, analyze complex networks, and transition into modern graph representation learning (GNNs). The course follows a seminar-based format. Students are expected to read the assigned seminal paper or book chapter before class and participate in critical discussions.

Text Vectorization

PhD Course, CuCEng, 2025

Course Objective

By the end of this course, students will understand the theoretical foundations behind transforming textual data into numerical representations that can be processed by machine learning models.
Starting from classical Vector Space Models and TF-IDF, the course explores a wide spectrum of embedding techniques up to modern Transformer-based contextual models. Students will gain both theoretical insight and practical implementation skills.

Theory of Computation

Undergraduate Course, CuCEng, 2025

Course Objectives

In this course, the main goal is to define the language classes in terms of grammars and automata.

Natural Language Processing

Undergraduate Course, CuCEng, 2026

Course Objectives

The primary objective of this course is to introduce classical Natural Language Processing (NLP) problems and explore their evolution. Students will learn the theoretical foundations of traditional approaches, follow the path from n-gram language models to Transformers, and transition to solving these problems using modern, locally-hosted Large Language Models (LLMs) via the Ollama ecosystem. The course heavily emphasizes engineering practices, strict structured output generation (JSON), evaluating model performance using standard metrics (BLEU, METEOR, chrF, ROUGE), and analyzing model limitations such as hallucinations and context window boundaries.

Modern NLP Systems

Undergraduate Course, CuCEng, 2027

Course Objectives

The primary objective of this course is to equip students with the practical engineering skills required to design, develop, and deploy modern Natural Language Processing systems based on Large Language Models (LLMs). The course aims to transition students from theoretical NLP concepts to building advanced, production-ready AI applications by utilizing state-of-the-art frameworks, external knowledge retrieval systems, and autonomous agent architectures.