Organisation
| Time | Monday, 8:15h-11:30h |
|---|---|
| Room | 056 |
| Credits | 4 SWS / 6 ECTS |
| Exam | written, 60min |
Announcements
- First lesson in summer term 2026: 23.03.2026
- Note that the contents of this course are totally different from it’s contents before summer term 26. The old contents are still described here old version of this lecture. The most important part of the old lecture - Machine Learning Algorithms - goes into a new lecture, which will be provided from winter term 26 on.
Artificial Intelligence
We are living in one of the most significant technological shifts in human history. Artificial Intelligence is no longer a futuristic concept confined to research labs — it is reshaping how we work, communicate, create, and make decisions, across every industry and corner of daily life. From healthcare diagnostics to autonomous vehicles, from legal research to creative writing, AI is becoming the defining technology of our time. As computer scientists, we are not just observers of this transformation — we are its architects. This makes our role both exciting and demanding. Understanding AI is no longer optional for software engineers and system designers. Whether you are building enterprise applications, designing user-facing products, or working on critical infrastructure, you will encounter AI-powered components, be expected to evaluate their capabilities, and be held responsible for their limitations and risks. Bias, hallucination, privacy violations, and security vulnerabilities are real challenges that only technically literate professionals can address effectively. This course is designed to give you exactly that literacy — and the practical skills to go with it. We will begin by building a solid conceptual foundation: the core categories of AI, the principles of machine learning, and the architecture behind Large Language Models (LLMs). From there, we will explore how LLMs power real-world systems — chatbots, Retrieval-Augmented Generation (RAG) pipelines, and autonomous AI agents. By the end of this course, you will be able to program these systems yourself. The future belongs to those who understand these tools deeply. Let’s get started.
Contents:
| Concepts of Artificial Intelligence, Machine Learning, Deep Learning and LLMs | |
| Basic Concepts of Artificial Intelligence and Machine Learning |
Intelligence and Artificial Intelligence (AI) AI Categories Machine Learning (ML) Categories Datastructure for ML Training, Validation and Test |
| Basic Concepts of Neural Networks | What a single Neuron
computes Basic concepts of Neural Networks How Neural Networks learn Single Layer Perceptron (SLP) |
| Single Layer Perceptron Learning Demo | SLP Training |
| Concepts of Deep Learning | What is Deep
Learning? Summary of Deep Learning Architectures Good Representations / Embeddings Transfer Learning and Self-Supervised Learning |
| Transformers and Large Language Models | Natural Language
Processing (NLP) Language Models Types of Transformers List of Popular LLMs Data for LLM training Self-Supervised, Supervised and Reinforcement Learning in LLMs |
| Preprocessing and Representation of Text | |
| Preprocessing and Representation of Text | Chunking and
Tokenisation Byte Pair Encoding Vector-Representations of Words and Texts Measuring Similarity Information Retrieval |
| Text Access and Processing Implementation 1 | Accessing Text from
Files and Websites Incomplete |
| Accessing GenAI models from the Cloud | |
| Access AI models from Hugging Face | Accessing Hugging
Face from Python Hugging Face Pipelines, Datasets, Model-Finetuning |
| Access LLMs from AcademicCloud and openAI | |
| From LLMs to Chatbots, RAG Systems and AI Agents | |
| Prompt Engineering | |
| Risks and Guardrail | |
| AI Agents | From LLMs to Chatbots to RAG to AI Agents |
| Evaluation | AI Agents evaluation criteria |
| Langchain Implementation of Prompting, RAG and Agents | |
| Basics of Langchain | |
| Prompt Engineering with Langchain | |
| Retrieval Augmented Generation with Langchain | |
| Implementation of AI-Agents with Langchain and Langgraph | |
Learning Material
- Jupyterbook of this lecture
- This course in Moodle
- Gitlab Repo for this course
- Python Precourse Video Tutorial
AI-Developer Certificate
If you plan to focus your Bachelor study on the subject of AI, the HdM Institute for Applied AI provides a bunch of AI-related lectures and you may go for the AI developer certificate. This lecture here (113441 Artifiicial Intelligence) is in the mandatory section for the AI-certificate.