teaching
SecretLLM course
SecretLLM: Behind the Secrets of Large Language Models
Period: Winter Semester 2024/2025 (planned for Winter Semester 2025/2026)
This course offers a practical and in-depth exploration of large language models (LLMs), which are at the core of modern natural language processing (NLP) systems. Students will gain hands-on experience alongside theoretical insights into LLM architecture, training methodologies, capabilities, and ethical considerations.
By the end of this course, students will be able to:
- Understand the architecture and key components of large language models.
- Analyze training processes, including data collection, model optimization, and fine-tuning.
- Evaluate the performance and limitations of LLMs across various NLP tasks.
- Apply LLMs to real-world applications, such as text generation, summarization, and translation.
- Discuss the ethical considerations and societal impacts of deploying LLMs.
Prerequisites
- Prior knowledge of Introduction to Machine Learning or an equivalent course.
- A basic understanding of neural networks.
- Programming experience in Python.
This course is offered together with Prof. Simon Razniewski.