Lecture: AI I - Advanced

Course content for the elective Artificial Intelligence II, focusing on advanced methods and hands-on AI applications.

Chapter

Prerequisites

Check the required knowledge and set up your programming environment to be ready for this module.

PyTorch & Deep Learning Basics

Learn the fundamentals of deep learning and how to implement neural networks using PyTorch.

1. Artificial Neuron
2. Multi Layer Perceptron

Training and Optimising Deep Networks

Learn techniques to effectively train and optimize deep learning models.

1. Regularization
2. Hyperparameter Tuning
3. Ensemble Learning

Advanced Techniques

Excursus

Computer Vision (excursus)

Have a look at some popular architectures and techniques used in computer vision tasks.

1. Convolutional Neural Networks
2. Residual Networks

Natural Language Processing (excursus)

Explore transformer architectures and their applications in natural language processing.

1. Transformer with GPT2
2. Sentiment Analysis with Transformers
3. Named Entity Recognition
4. AI Agent

Assessment

Apply your knowledge in practical assessments to demonstrate your skills in machine learning, optimization, and evaluation.

1. Assessment 1:
2. Assessment 2:

Getting Started

Note

Use the included dev container to automatically install all the necessary dev tools and dependencies. To use this you first need to install docker under Linux or WSL2 under windows.

1. Clone the repository:

   git clone https://github.com/Paul-B98/python-project-template.git
   cd python-project-template

2. Open the project in Visual Studio Code:

   code .

3. Reopen in container:

   • Press F1 to open the command palette.
   • Type Remote-Containers: Reopen in Container and select it.
   • VS Code will build the Docker container defined in the .devcontainer folder and open the project inside the container.

Contributing

Conventional Commits

We follow the Conventional Commits specification to maintain a consistent commit history and enable automated tooling for releases and changelogs.

Commit message format:

Commit Message Format

<type>(optional scope): <short summary>

[optional body]

[optional footer(s)]

Common Types

• feat: A new feature
• fix: A bug fix
• docs: Documentation only changes
• style: Changes that do not affect the meaning of the code (formatting, missing semicolons, etc.)
• refactor: A code change that neither fixes a bug nor adds a feature
• perf: A code change that improves performance
• test: Adding or correcting tests
• chore: Changes to the build process or auxiliary tools
• infra: infrastructure ch

Documentation

• Contributing: A guide on how to contribute to this project, including commit conventions and best practices.