The aim of the course is to acquire basic knowledge on deep learning. This includes classical neural network models and recent deep architectures. Topics such as convolutional neural networks, optimisation, regularisation, generative models, sequential models will be covered among others. In the exercise, the participants will implement some of the standard models for classification or regression, transfer learning, generative models and acquire knowledge on machine learning applications.
Please register directly in Moodle, in the first two weeks of the semerster you do not need an access code. Afterwards you can obtain the code in the lecture itself.
You can find the links on campusonline.uni-ulm.de or you can seach for the course on moodle.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. www.deeplearningbook.org
Rojas, R. (2013). Neural networks: a systematic introduction.
Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning.
The information displayed on this page is for general information only and may not be complete. For legal binding information, please consult the currently active Modulhandbuch/FSPO of the respective study program. Day-to-day information is provided through the moodle page of the respective course (registration required).