Peter Bosman (CWI) Awarded €1mn NWO Open Technology Programme Grant
Peter Bosman’s project proposal DAEDALUS (Distributed and Automated Evolutionary Deep Architecture Learning with Unprecedented Scalability) has been accepted by NWO TTW through its Open Technology Programme.
Senior researcher at CWI’s Life Sciences & Health Group, Peter Bosman will develop new technology to automate the search for the most suitable deep neural network architectures to tackle a specific task in a way that scales much better than existing approaches. Bosman is doing this in collaboration with research partner Leids Universitair Medisch Centrum (LUMC) and industry partners Elekta and Ortec Logiqcare.
While the technology will generally be widely applicable, a key motivation driving the project will be applications in the medical domain. Therefore, the researchers want to develop variants of the new technology for when data is spread across multiple locations. This is important because for state-of-the-art results, much training data is typically needed, while individual hospitals typically only have limited data and sharing patient data between hospitals is often non-trivial. Solutions will be created for the case when data can be pooled in one location as well as when only information on learned models can be shared.
Real-world use-cases and demonstration of the potential of this new technology is aimed to be achieved within the project runtime through two applications in radiation oncology. The research team will consist of 1 postdoc, 1 PhD student, and 1 scientific programmer for CWI as well as 1 PhD student based at LUMC. Furthermore, international collaborations are planned with renowned researchers at the University of Texas and the Virginia Commonwealth University in the USA, the University of Queensland in Australia, and the Victoria University of Wellington in New Zealand.