Friedrich-Alexander-Universität Erlangen

Lehrstuhl für Mustererkennung

Martensstraße 3

91058 Erlangen

There is a high demand for free resources concerning deep learning. For this reason, we decided to host our lecture video recordings online. Note that the lecture is adapted each semester to incorporate the latest state-of-the-art.

Video Lecture Winter 2018/2019

Furthermore, we have a short summary of the most important parts of the lecture hosted as introduction to deep learning. Note that this document is only supplementary material to the lecture and does not contain enough information to pass the oral exam.

Note that the material is licensed under Creative Commons 4.0 Attribution License. Feel free to share and reuse!

Another excellent supplementary material are the iPython Notebooks that we created for the MICCAI Educational Challenge 2018. They are available for download at GitHub.

We created this material to make access to deep learning image reconstruction and known operator learning as easy as possible. The theory including a refresher on deep learning and reconstruction basics is found in the first presentation Deep Learning Computed Tomography & Known Operator Learning Theory. Next, we prepared an introduction to PYRO-NN and its concepts in Introduction PYRO-NN. Finally, we give extended comments to example code in Coding Examples using PYRO-NN. Same code is also available online to experiment & modify in our Online PYRO-NN Experimentation Environment.

Deep Learning Computed Tomography & Known Operator Learning Theory