Teaching · Fall 2026–2027
AIE 640 Artificial Intelligence Applications
This graduate course provides a comprehensive and practical introduction to modern Artificial Intelligence applications built on Large Language Models (LLMs). Through hands-on implementation and experimentation, students learn the fundamental concepts, practical applications, and advanced techniques for working with LLMs — from understanding their inner workings to fine-tuning and deployment. The course follows the O'Reilly book "Hands-On Large Language Models" by Jay Alammar and Maarten Grootendorst, emphasizing visual learning and practical implementation.
- Programme
- MSc Artificial Intelligence, Institute of Informatics
- Duration
- 14 weeks · 3 credits
- Prerequisites
- Python programming, basic machine learning concepts, linear algebra
- Turkish title
- Yapay Zekâ Uygulamaları
Learning objectives
- Understand the fundamental architecture and mechanisms of transformer-based LLMs
- Implement text classification, clustering, and semantic search systems using pre-trained models
- Design and optimize prompts for various NLP tasks
- Build retrieval-augmented generation (RAG) systems
- Fine-tune language models for specific tasks
- Develop multimodal applications using vision-language models
- Deploy and scale LLM applications in production environments
Weekly plan
| Week | Topic | Book chapter | Due |
|---|---|---|---|
| 1 | Course Introduction & LLM Foundations | Ch. 1 – Introduction to Language Models | |
| 2 | Understanding Text Representation | Ch. 2 – Token Embeddings | |
| 3 | Transformer Architecture Deep Dive | Ch. 3 – Looking Inside Transformer LLMs | |
| 4 | Text Classification Systems | Ch. 4 – Text Classification | |
| 5 | Unsupervised Text Analysis | Ch. 5 – Text Clustering and Topic Modeling | HW1 (covers Weeks 1–4) — 22 Oct, 23:59 · Paper proposal — extended to 29 Oct, 23:59 |
| 6 | Prompt Engineering Mastery | Ch. 6 – Prompt Engineering | |
| 7 | Advanced Generation Techniques | Ch. 7 – Advanced Text Generation Techniques and Tools | HW2 (covers Weeks 5–6) — 12 Nov, 23:59 |
| 8 | Semantic Search & RAG Systems | Ch. 8 – Semantic Search and Retrieval-Augmented Generation | |
| 9 | Multimodal AI Applications | Ch. 9 – Multimodal Large Language Models | HW3 (covers Weeks 7–8) — 26 Nov, 23:59 |
| 10 | Creating Custom Embeddings | Ch. 10 – Creating Text Embedding Models | Progress report (draft paper with preliminary results) — 3 Dec, 23:59 |
| 11 | Fine-tuning for Classification | Ch. 11 – Fine-Tuning Representation Models for Classification | |
| 12 | Fine-tuning Generative Models | Ch. 12 – Fine-Tuning Generation Models | |
| 13 | Student Project Presentations IFinal Project Presentations – Session 1 | — | HW4 (covers Weeks 9–12) — 24 Dec, 23:59 · Presentation slides (all groups) — 23 Dec, 23:59 |
| 14 | Student Project Presentations II & Course Wrap-upFinal Project Presentations – Session 2 & Course Summary | — |
Assessment
| Component | Weight | Due |
|---|---|---|
| Paper proposal | 10% | 29 Oct (extended from Week 5) |
| Homework assignments (4 × 5%) | 20% | Weeks 5, 7, 9, 13 (22 Oct, 12 Nov, 26 Nov, 24 Dec) |
| Project & research paper | 70% | Progress report Week 10 (3 Dec); presentations Weeks 13–14 (slides due 23 Dec); final paper in finals week (date TBA) |
The weekly practice exercises in the weekly schedule are ungraded; the four graded homework assignments each cover a block of weeks (HW1: Weeks 1–4, HW2: Weeks 5–6, HW3: Weeks 7–8, HW4: Weeks 9–12). All deadlines are 23:59 Turkey time on the date shown. The project is an original research study on transformers, LLMs and their applications, written up as a research paper; see the project guidelines and proposal rubric.
Resources
- Primary Textbook: "Hands-On Large Language Models" by Jay Alammar and Maarten Grootendorst
- Original Code Repository: GitHub – HandsOnLLM. Note: the notebooks in this repository are extended versions of the ones from the book.
- Platform: Google Colab (recommended) or a local Python environment
- Hardware: Access to GPU resources (T4 or better)