Studienhandbuch | UE Hands-on AI I

Inhalt

Workload	Education level	Study areas	Responsible person	Hours per week	Coordinating university
1,5 ECTS	B1 - Bachelor's programme 1. year	^(*)Artificial Intelligence	Rainer Dangl	1 hpw	Johannes Kepler University Linz

Detailed information

Original study plan

Bachelor's programme Artificial Intelligence 2025W

Learning Outcomes

Competences
Students are able to handle, preprocess, and visualize different types of datasets, and apply foundational deep learning techniques for practical problem-solving. Students are capable of developing, training, and optimizing artificial neural networks using deep learning frameworks like PyTorch, including understanding and applying techniques like gradient descent, batch normalization, and dropout.

Skills	Knowledge
Handling and understanding of different kinds of data sets Visualization, dimensionality reduction and clustering of data Moving from Linear Regression to Logistic Regression and Artificial Neural Networks Understanding gradient descent Using Deep Learning frameworks like PyTorch Playing around with the first Artificial Neural Networks Introducing Convolutional Neural Networks Tips and tricks for making networks learn (batch normalization, dropout, transfer learning, etc.)	Students possess foundational knowledge of deep learning concepts, including neural networks, gradient descent, data visualization, and handling of various types of datasets. They understand the use of AI frameworks like PyTorch and are familiar with optimization techniques and deep learning architectures like Convolutional Neural Networks.

Criteria for evaluation

Online Assignments

Language

English

Changing subject?

Corresponding lecture

in collaboration with 536AIBAHO1V20: VL Hands-on AI I (1.5 ECTS) equivalent to
536AIBAHO1K19: KV Hands-on AI I (3 ECTS)

On-site course
Maximum number of participants	35
Assignment procedure	Direct assignment