University of Applied Sciences of Western Switzerland: Sr Research Data Scientist (Medical Scheduling)
Seeking a senior research data scientist to participate in the "Optimizing Operating Rooms and Care Services using Deep Reinforcement Learning" project.
At: University of Applied Sciences of Western Switzerland
Location: Yverdon-les-Bains, Switzerland
Position: Sr Research Data Scientist (Medical Scheduling)
The Institute for Information and Communication Technologies (IICT), HES-SO/campus HEIG-Vd/Y-Parc, Yverdon-les-Bains, Switzerland, has an opening for a senior research data scientist to participate in the "Optimizing Operating Rooms and Care Services using Deep Reinforcement Learning" project.
We have the following requirements:
- PhD in mathematics (possibly related to data science), theoretical physics, statistics, computer science, or related disciplines.
- Very good knowledge of Python, Java or a similar programming language
- Excellent publication record
- Very competitive remuneration package
- Opportunity to collaborate with Swiss, US and Korean researchers from reputable institutions (i.e. University of Urbana-Champaign, MIT, Seoul National University,…) and start-ups
The primary focus of the data scientist will be to perform research within the framework of a project in collaboration with Calyps but the future candidate will also be encouraged to pursue and spend time for his own research.
In this project we want to create a new scheduler, modelled as a direct acyclic graph, which is a modern way to represent scheduling problems and which can include complex dependencies and heterogeneous demands, in addition to be flexible and efficient. Relaxing one or the other of the constraints leads to NP-complete problems already. Furthermore it is possible to automate it, i.e. when adding a new constraint, which would require a “re-design” with standard methods. Algorithms over graphs are generally designed by human experts but to meet very strong performances it becomes more and more challenging as the algorithmic literature is limited. What we aim to do here is to apply deep learning methods to challenging graph based optimization problems. The graph-structured data needs to be “transformed” into a Euclidian space before deep learning methods can be used. There is a family of representations called graph convolutional neural networks but they are quite specific to particular graphs, inspired essentially from images. There is a need of further understanding in this area and an adaptation to our scheduling problem. Once this step is done we would like to apply deep neural network techniques, or reinforcement learning methods to the problem of obtaining optimal schedules. The second step concerns the learning part, from the sequence to the schedule. As stated the “timeseries” format is very well adapted for neural networks. Advantage of this representation is that it is not limited. We suggest recurrent neural networks to be compared with reinforcement learning techniques to maximize the reward over time. Applying neural networks techniques based learning on graphs can lead to much more flexibility for being able to optimize complex schedules over time.
This is a 12-month position, eventually renewable. It must start as soon as possible, when the candidate is available. A good working knowledge in English is required (no other language is needed). Applications, including a resume, a list of publications, and the name of at least three referees (physical and email addresses, phones numbers) should be sent as soon as possible to firstname.lastname@example.org (MS Word, .pdf, .ps or plain text).