DeepHealth Winter School was held in January 24th, 2022 – January 28th, 2022. It was an intense week in which the combination of lectures and lab exercises (see the program in the figure below) brought participants closer to a) the use of deep learning and computer vision in tasks related to medical imaging and other medical data, and b) to high-performance computing to considerably reduce the running times of model-training processes. The winter school also included one session devoted to other projects of the same ICT-11-2018 call: LEXIS and CYBELE.
It was designed for an audience with a background in Computer Science, whereas it was open to everybody and reached 70 connected participants on average each day. The target people, considered for designing the contents of the winter school, were PhD and Master’s degree students in AI/ML/DS and professionals from the Industry with previous knowledge of Machine Learning. Additionally, due to the fact that the proposed lab exercises were designed to be run on Linux machines, experience with Linux and shell-script was recommended to all audience types.
Lab sessions were open to all registered people, even for those who registered for master classes only. All the attendees could run the non-distributed experiments in their own computers if equipped with one GPU at least. Even now, any interested person can download the datasets and the code, and following the guides, can reproduce the experiments.
All the material (slides, code and guides for lab exercises) is available in the GitHub public repository at https://github.com/deephealthproject/winter-school.
