de | en

Practical Course - Deep Learning from Scratch in C++ (IN2106, IN0012, IN4259)

Course 0000004058 in SS 2019

General Data

Course Type practical training
Semester Weekly Hours 6 SWS
Organisational Unit Informatics 16 - Chair of Computer Aided Medical Procedures (Prof. Navab)
Lecturers Tobias Lasser
Theodor Cheslerean Boghiu
Josue Page
Anca-Elena Stefanoiu
Dates Wed, 14:00–16:00, MI 03.13.010
and 3 singular or moved dates

Assignment to Modules

Further Information

Courses are together with exams the building blocks for modules. Please keep in mind that information on the contents, learning outcomes and, especially examination conditions are given on the module level only – see section "Assignment to Modules" above.

additional remarks In this lab course "Deep Learning from Scratch in C++" the focus is on implementing deep learning techniques from scratch in modern C++17, with the aim of solving an exciting real world problem in medical imaging. Starting from scratch, all of the heavy lifting required for deep learning is to be implemented in a modern, platform-independent C++17 library using the CMake build system, with Python bindings for actually using the library. You will be guided by the tutors in weekly or bi-weekly sessions during the term on what is required and expected in terms of functionality, and will incrementally implement all the necessary functionality. As the culmination at the end of the term, you will use your library to solve a real world problem in medical imaging.
Links Course documents
E-Learning course (e. g. Moodle)
TUMonline entry
Top of page