Nach positiver Absolvierung der Lehrveranstaltung sind Studierende in der Lage grundlegende Verfahren im Bereich Machine Learning zu verstehen und typische Probleme mit modernen Verfahren des ML zu lösen.
After successful completion of the course, students are able to
1. Remembering: the students will be able to understand the basic problems in classification and machine learning.
2. Understanding: the students will be able to understand typical problems such as neural networks and support vector machines.
3. Applying: the students will be able to apply the proposed solutions.
4. Analysing: the students will be able to analyse the proposed solutions.
5. Synthesising: the students will be able to include the proposed solutions in a larger context.
6. Assessing: the students will be able to critically assess the performance of current techniques.
With this the students will be prepared to work within an Austrian or European enterprise.
The course provides a practical and theoretical overview of machine learning methods: General concepts of machine learning (supervised vs. unsupervised approaches, generalization and overfitting, regularization techniques, evaluation methods, cross-validation, early stopping). Basic regression and classification algorithms (least squares, perceptron and logistic regression). Basics of clustering (Lloyd, kMeans). Nonlinear extensions through the kernel trick (support vector machines, kernel ridge). Gradient descent and neural networks (backprogation, LMS, RLS, Newton). Domain specific layers (Recursive and convolutional networks) and unsupervised neural networks (autoencoders).
The lectures are complemented by four exercise classes with a focus on practical implementations in Tensorflow and Numpy. Basic Python knowledge is beneficial but not required. At the end of the course, the students will work on a practical project, undergoing a complete machine-learning pipeline on a real-world dataset. Here we also cover more advanced topics (adversarial networks, transfer learning).
Erste Vorlesung findet am 4.10.2024, 14Uhr-15:00Uhr im EI1 in Präsenz statt.
This year's exercise classes will be held on:
25.10.24
22.11.24
13.12.24
10.01.25