Qualification objectives: The students have a basic understanding of algebraic and computational methods for deep neural networks, their application scope and can practically build and train them with state-of-the-art software tools. They are familiar with typical deep learning structures and understand the relationship to their shallow counterparts.
- Multilayer neural network and universal represenation theorem
- Deep feedforward networks
- Convolutional Neural Networks
- Autoencoder versus principal component analysis
- Time-autoencoder versus time-lagged independent component analysis
- Generative networks: Variational Autoencoders and Adversarial Generative Networks
- Active learning
This lecture/lab course is suitable for Master students of Mathematics, Computer Science, Computational Sciences and Physics.
Students of the Computational Sciences program can combine this lecture/lab course with 19234502 + 19234501 (Mathematical aspects in machine learning) to complete “complex algorithms A/B”
Physics students please contact the Exam Office, dmitrij.heinz(at)fu-berlin.de, indicating modul and matriculation number
Virtueller Raum 23
wöchentlich, ab 16.04.2021, 14:00 - 16:00 (14 Termine)