ISTINYE UNIVERSITY BİLGİ PAKETİ / DERS KATALOĞU
| Computer Engineering (English) | |||||
| Bachelor | TR-NQF-HE: Level 6 | QF-EHEA: First Cycle | EQF-LLL: Level 6 | ||
Course Introduction and Application Information
| Course Code: | SWE015 | ||||
| Course Name: | Introduction to Large Language Models | ||||
| Semester: |
Fall Spring |
||||
| Course Credits: |
|
||||
| Language of instruction: | English | ||||
| Course Condition: | |||||
| Does the Course Require Work Experience?: | No | ||||
| Type of course: | Departmental Elective | ||||
| Course Level: |
|
||||
| Mode of Delivery: | E-Learning | ||||
| Course Coordinator: | Dr. Öğr. Üy. ALPER ÖNER | ||||
| Course Lecturer(s): | Assist. Prof. Dr. Alper Öner, Res. Assist. Yazım Beril Uluer | ||||
| Course Assistants: |
Course Objective and Content
| Course Objectives: | The aim of the large language model development course is to provide individuals specialized in natural language processing (NLP) with knowledge and skills in creating, training and developing large language models. This course provides in-depth knowledge of understanding complex language structures, performing language-based tasks, and using language models effectively in real-world applications. |
| Course Content: | Docker, Tensorflow, Neural Network, Convolutional Neural Network, Introduction to Neural Language Processing, Tranformers-BERT & NER, LLM, LLM Finetuning, MLLM , Computer Vision and Neural Language Processing Applications |
Learning Outcomes
|
The students who have succeeded in this course;
1) Design a well-defined problem formulation for a basic LLM problem. 2) Develop optimized LLM. 3) Will apply software tools to solve LLM problems. 4) Will be able to solve Basic Image Processing and Language Problems with transformers methods. 5) Will be able to realize a Transformers Project as a team. |
Course Flow Plan
| Week | Subject | Related Preparation |
| 1) | Docker – GIT | |
| 2) | Neural Networks - Tensorflow | |
| 3) | Convolutional Neural Network | |
| 4) | Deep Learning for Computer Vision | |
| 5) | Introduction to Neural Language Processing | |
| 6) | Deep Learning for Neural Language Processing | |
| 7) | Tranformers-BERT & NER | |
| 8) | Midterm Exam | |
| 9) | Multilingual Named Entity Recognition with Transformers | |
| 10) | Making Transformers Efficient in Production | |
| 11) | Large Language Models (LLM) | |
| 12) | Open Source Large Language Models (LLM) | |
| 13) | Foundation Models | |
| 14) | LLM Applications |
Sources
| Course Notes / Textbooks: | Natural Language Processing with Transformers, Lewis Tunstall, Leandro von Werra, and Thomas Wolf, O’Reilly. |
| References: | Deep Learning with Python, François Chollet, Manning, 2018. |
Course - Program Learning Outcome Relationship
| Course Learning Outcomes | 1 |
2 |
3 |
4 |
5 |
||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Program Outcomes | |||||||||||
| 1) Adequate knowledge in mathematics, science, and computer engineering principles, both theoretical and practical, and the ability to apply this knowledge to complex engineering problems. | 2 | 2 | 2 | 2 | 2 | ||||||
| 2) Ability to identify, formulate, and solve complex computer engineering problems using appropriate analysis and modeling techniques. | 2 | 2 | 2 | 2 | 2 | ||||||
| 3) Ability to design and develop complex computer systems, devices, or products that meet specific requirements and operate under realistic constraints and conditions, using modern design methods. | 2 | 2 | 2 | 2 | 2 | ||||||
| 4) Ability to develop, select and use modern techniques and tools used for the analysis and solution of complex computer engineering problems, and the ability to use information technologies effectively. | 3 | 2 | 3 | 3 | 3 | ||||||
| 5) Ability to plan and conduct experiments, collect and analyze data, and interpret results in the study of complex computer engineering problems or research topics. | 2 | 2 | 2 | 2 | 2 | ||||||
| 6) Ability to work effectively within and multidisciplinary teams; individual study skills. | |||||||||||
| 7) Ability to communicate effectively orally and in writing; knowledge of at least one foreign language; ability to write effective reports and understand written reports, to prepare design and production reports, to make effective presentations, to give and receive clear and understandable instructions. | |||||||||||
| 8) Awareness of the necessity of lifelong learning; ability to access information, to follow developments in science and technology and to renew continuously. | |||||||||||
| 9) To act in accordance with ethical principles, professional and ethical responsibility; information on the standards used in engineering applications. | |||||||||||
| 10) Information on business practices such as project management, risk management and change management; awareness of entrepreneurship and innovation; information about sustainable development. | 3 | ||||||||||
| 11) Knowledge of the effects of computer engineering practices on health, environment and safety in the universal and social scale and the problems of the era reflected in computer engineering; awareness of the legal consequences of computer engineering solutions. | |||||||||||
Course - Learning Outcome Relationship
| No Effect | 1 Lowest | 2 Average | 3 Highest |
| Program Outcomes | Level of Contribution | |
| 1) | Adequate knowledge in mathematics, science, and computer engineering principles, both theoretical and practical, and the ability to apply this knowledge to complex engineering problems. | 2 |
| 2) | Ability to identify, formulate, and solve complex computer engineering problems using appropriate analysis and modeling techniques. | 2 |
| 3) | Ability to design and develop complex computer systems, devices, or products that meet specific requirements and operate under realistic constraints and conditions, using modern design methods. | 3 |
| 4) | Ability to develop, select and use modern techniques and tools used for the analysis and solution of complex computer engineering problems, and the ability to use information technologies effectively. | 2 |
| 5) | Ability to plan and conduct experiments, collect and analyze data, and interpret results in the study of complex computer engineering problems or research topics. | 2 |
| 6) | Ability to work effectively within and multidisciplinary teams; individual study skills. | |
| 7) | Ability to communicate effectively orally and in writing; knowledge of at least one foreign language; ability to write effective reports and understand written reports, to prepare design and production reports, to make effective presentations, to give and receive clear and understandable instructions. | |
| 8) | Awareness of the necessity of lifelong learning; ability to access information, to follow developments in science and technology and to renew continuously. | |
| 9) | To act in accordance with ethical principles, professional and ethical responsibility; information on the standards used in engineering applications. | |
| 10) | Information on business practices such as project management, risk management and change management; awareness of entrepreneurship and innovation; information about sustainable development. | |
| 11) | Knowledge of the effects of computer engineering practices on health, environment and safety in the universal and social scale and the problems of the era reflected in computer engineering; awareness of the legal consequences of computer engineering solutions. |
Assessment & Grading
| Semester Requirements | Number of Activities | Level of Contribution |
| Homework Assignments | 2 | % 20 |
| Project | 2 | % 40 |
| Final | 1 | % 40 |
| total | % 100 | |
| PERCENTAGE OF SEMESTER WORK | % 60 | |
| PERCENTAGE OF FINAL WORK | % 40 | |
| total | % 100 | |
Workload and ECTS Credit Calculation
| Activities | Number of Activities | Workload |
| Course Hours | 14 | 42 |
| Presentations / Seminar | 3 | 25 |
| Project | 3 | 28 |
| Homework Assignments | 4 | 20 |
| Final | 2 | 20 |
| Total Workload | 135 | |