TÜRKÇE
ENGLISH
Information
| Unit | FACULTY OF ENGINEERING |
| COMPUTER ENGINEERING PR. (ENGLISH) | |
| Code | CEN472 |
| Name | Modern NLP Systems |
| Term | 2026-2027 Academic Year |
| Semester | 8. Semester |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 6 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | İngilizce |
| Level | Belirsiz |
| Type | Normal |
| Label | E Elective |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Prof. Dr. UMUT ORHAN |
| Course Instructor |
The current term course schedule has not been prepared yet.
|
Course Goal / Objective
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.
Course Content
This project-centric course covers the end-to-end integration of LLMs into modern software systems. Key topics include the architecture and implementation of Retrieval-Augmented Generation (RAG) pipelines, vector database management, and chunking strategies for semantic search. The curriculum also focuses on adapting open-source models to domain-specific tasks using Parameter-Efficient Fine-Tuning (PEFT) and LoRA methodologies. Furthermore, students will explore agentic workflows, function calling, and tool integration using frameworks like LangChain and LlamaIndex. Through hands-on labs and team projects, students will develop and deploy functional AI prototypes capable of solving complex, real-world scenarios.
Course Precondition
none
Resources
Raschka, S. (2024). Build a Large Language Model (From Scratch). Manning Publications. (Büyük dil modellerinin sıfırdan nasıl kodlandığını, donanım optimizasyonlarını ve ince ayar süreçlerini anlamak için başucu kitabıdır.) Tunstall, L., von Werra, L., & Wolf, T. (2022). Natural Language Processing with Transformers: Building Language Applications with Hugging Face. O'Reilly Media. (Açık kaynak ekosistemini kullanmak için pratik rehber).
Notes
Raschka, S. (2024). Build a Large Language Model (From Scratch). Manning Publications. (Büyük dil modellerinin sıfırdan nasıl kodlandığını, donanım optimizasyonlarını ve ince ayar süreçlerini anlamak için başucu kitabıdır.) Tunstall, L., von Werra, L., & Wolf, T. (2022). Natural Language Processing with Transformers: Building Language Applications with Hugging Face. O'Reilly Media. (Açık kaynak ekosistemini kullanmak için pratik rehber).
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Knows the integration principles of large language models into modern software systems and the theoretical background of Retrieval-Augmented Generation (RAG) architecture |
| LO02 | Knows the conceptual logic behind autonomous agent mechanisms that enable large language models to communicate with external tools and parameter-efficient fine-tuning (PEFT) processes |
| LO03 | Accomplishes developing an interactive AI application augmented with external data sources (RAG) using vector databases and semantic search strategies |
| LO04 | Accomplishes training an open-source language model on a specific dataset with parameter-efficient fine-tuning (PEFT/LoRA) methods and running it in a local environment |
| LO05 | Accomplishes coding autonomous agents that interact with external tools (APIs, web search) and solve multi-step tasks using modern frameworks (LangChain/LlamaIndex, etc.) |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | Adequate knowledge of mathematics, science and related engineering disciplines; ability to use theoretical and applied knowledge in these fields in solving complex engineering problems. | 3 |
| PLO02 | Bilgi - Kuramsal, Olgusal | Ability to identify, formulate and solve complex engineering problems; ability to select and apply appropriate analysis and modeling methods for this purpose. | 4 |
| PLO03 | Bilgi - Kuramsal, Olgusal | Ability to design a complex system, process, device or product to meet specific requirements under realistic constraints and conditions; ability to apply modern design methods for this purpose. | 5 |
| PLO04 | Bilgi - Kuramsal, Olgusal | Ability to select and use modern techniques and tools necessary for the analysis and solution of complex problems encountered in engineering practice; ability to use information technologies effectively. | 4 |
| PLO05 | Bilgi - Kuramsal, Olgusal | Ability to design and conduct experiments, collect data, analyze and interpret results to investigate complex engineering problems or discipline-specific research topics. | 3 |
| PLO06 | Bilgi - Kuramsal, Olgusal | Ability to work effectively in interdisciplinary and multidisciplinary teams; individual working skills. | |
| PLO07 | Bilgi - Kuramsal, Olgusal | Ability to communicate effectively verbally and in writing; knowledge of at least one foreign language; ability to write effective reports and understand written reports, prepare design and production reports, make effective presentations, and give and receive clear and understandable instructions. | |
| PLO08 | Bilgi - Kuramsal, Olgusal | Awareness of the necessity of lifelong learning; ability to access information, follow developments in science and technology, and constantly renew oneself. | |
| PLO09 | Bilgi - Kuramsal, Olgusal | Knowledge of ethical principles, professional and ethical responsibility, and standards used in engineering practice. | |
| PLO10 | Bilgi - Kuramsal, Olgusal | Knowledge of business practices such as project management, risk management and change management; awareness of entrepreneurship and innovation; knowledge of sustainable development. | 3 |
| PLO11 | Bilgi - Kuramsal, Olgusal | Knowledge of the effects of engineering practices on health, environment and safety in universal and social dimensions and the problems of the age reflected in the field of engineering; awareness of the legal consequences of engineering solutions. |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Introduction to Modern NLP Systems and API Ecosystem | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım |
| 2 | Vector Spaces, Embedding Models, and Semantic Search | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Gösterip Yaptırma |
| 3 | Vector Database Management and Text Chunking Strategies | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 4 | Implementation of RAG (Retrieval-Augmented Generation) Architecture | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 5 | RAG Systems Project Delivery and Application Development (UI/UX) | Implementational presentations | Öğretim Yöntemleri: Anlatım, Tartışma |
| 6 | Open Source Language Models and the Hugging Face Ecosystem | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 7 | Dataset Preparation and Formatting for Language Models | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 8 | Project presentation | Implementational presentations | Ölçme Yöntemleri: Proje / Tasarım |
| 9 | Parameter-Efficient Fine-Tuning (PEFT) and the Math of LoRA | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 10 | Open Source Model Training (Fine-Tuning) on Local Hardware | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 11 | Delivery of Fine-Tuned Domain-Specific Models | Reading related chapter in lecture notes | Ölçme Yöntemleri: Proje / Tasarım |
| 12 | Function Calling and Tool Use in Large Language Models | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 13 | Autonomous Agent Architectures and LangChain-LlamaIndex Frameworks | Reading related chapter in lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 14 | Agentic Workflows Project Delivery and Live Demos | Reading related chapter in lecture notes | Ölçme Yöntemleri: Proje / Tasarım |
| 15 | Delivery of projects | Implementational presentations | Ölçme Yöntemleri: Proje / Tasarım |
| 16 | Term Exams | Reviewing Lecure Notes and applications | Ölçme Yöntemleri: Yazılı Sınav |
| 17 | Term Exams | Yöntem Seçilmemiş |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
| Out of Class Study (Preliminary Work, Practice) | 14 | 2 | 28 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 3 | 20 | 60 |
| Mid-term Exams (Written, Oral, etc.) | 0 | 0 | 0 |
| Final Exam | 1 | 20 | 20 |
| Total Workload (Hour) | 150 | ||
| Total Workload / 25 (h) | 6,00 | ||
| ECTS | 6 ECTS | ||