Training and Understanding Modern Deep Networks
||Training and Understanding Modern Deep Networks|
||Hossein Azizpour <email@example.com>|
||Kungliga Tekniska högskolan|
||2022-03-02 – 2022-10-01|
This proposal is for the scientific studies within the group of Hossein Azizpour. In Azizpour's group we try to understand modern deep networks and train them for impactful applications. Therefore, there are two main types of projects in the group. One is on the fundamentals of deep learning and the other on the application side.
Fundamental of deep networks: here three main tracks are pursued for the foundations of trustworthy deep network: (i) interpreting and understanding trained deep networks especially from the lens of a functional analysis, (ii) explaining individual decisions of a trained deep network in a human-interpretable way, and (iii) quantification and robustness to uncertainty in the decisions of a trained deep network.
Applications: on the application side, we apply the findings of the fundamental research on a few impactful applications including: (i) general computer vision, (ii) breast cancer diagnosis and prognosis specifically estimating risk of cancer and explaining the predictions, (iii) earth observation, especially uncertainty in the developments for detecting urbanization and forest fires, and (iv) protein structure modelling, especially the interpretable models and uncertainty of predictions.
As such all of the directions are either purely empirical or require empirical validations of the theories. Such empirical investigations for modern deep networks such as large ResNets and visual transformers can only be enabled with the help of a large GPU cluster such as Berzelius.
This proposal is for unifying all the ongoing projects within Azizpour's group. Currently the active projects that will be merged into this proposal are:
Upon an approval of this project, all computations and storages are going to be transferred into this project and the current subprojects can be cancelled.