PhD studentship - Neural network analysis of quantum processes
- Employer
- Global Academy Jobs
- Location
- United Kingdom
- Closing date
- May 31, 2019
View more
- Sector
- Science, Physical Sciences and Engineering, Physics, Chemistry, Biochemistry, Pharmaceutical, Business Development
- Hours
- Full Time
- Organization Type
- University and College
- Jobseeker Type
- Academic (e.g. 'Lecturer')
You need to sign in or create an account to save a job.
Job Details
Project description
Earlier this year, the Spin Dynamics group at the University of Southampton created a family of neural networks that recovered molecular distance distributions from magnetic spectroscopy data (DOI: 10.1126/sciadv.aat5218). The networks reliably returned distance data for proteins, nucleic acids, photosynthetic reaction centres, and other systems of current chemical and biological interest. The principal problem is that... this was not supposed to be possible: the mathematical transformations in question are ill-posed and numerically unstable. At the moment, we have no slightest idea how those neural networks accomplish what is technically, without regularisation, an impossible mathematical operation.
The objective of this project is to find out. It will make use of one of the biggest supercomputers in the UK to run neural network training against quantum mechanical simulations of spin dynamics in biological systems. The resulting networks will be taken apart with the purpose of finding out how exactly they work. The conclusions will have significance across physical sciences - at the moment, the internal functioning of artificial neural networks is largely a mystery.
It is likely that the student will make a major contribution to both quantum theory and artificial intelligence by exploring, developing, and analysing neural networks that process spectroscopic data. This project is a collaboration with ETH Zurich (Prof Gunnar Jeschke) and Weizmann Institute (Prof Daniella Goldfarb), and will involve visits to both of these institutions.
Details
This is a 4-year studentship; it is open to UK and EU nationals, and includes all applicable university fees, as well as a tax-free stipend of £15,009 per year.
Due to funding restrictions this position is only open to UK students and EU students who meet the RCUK eligibility criteria
Application process
Applications for a PhD in Chemistry should be submitted online at https://studentrecords.soton.ac.uk/BNNRPROD/bzsksrch.P_Search
Please ensure you select the academic session 2019-20 when making your application in the academic year field and click on the Research radio button. Enter Chemistry in the search text field
Informal enquiries should be sent to Ilya Kuprov ( i.kuprov@soton.ac.uk ).
Any queries on the application process should be made to feps-pgr-apply@soton.ac.uk
The University of Southampton and the School of Chemistry both hold Athena SWAN Silver Awards, reflecting their commitment to equality, diversity and inclusion, and particularly to gender equality.
Earlier this year, the Spin Dynamics group at the University of Southampton created a family of neural networks that recovered molecular distance distributions from magnetic spectroscopy data (DOI: 10.1126/sciadv.aat5218). The networks reliably returned distance data for proteins, nucleic acids, photosynthetic reaction centres, and other systems of current chemical and biological interest. The principal problem is that... this was not supposed to be possible: the mathematical transformations in question are ill-posed and numerically unstable. At the moment, we have no slightest idea how those neural networks accomplish what is technically, without regularisation, an impossible mathematical operation.
The objective of this project is to find out. It will make use of one of the biggest supercomputers in the UK to run neural network training against quantum mechanical simulations of spin dynamics in biological systems. The resulting networks will be taken apart with the purpose of finding out how exactly they work. The conclusions will have significance across physical sciences - at the moment, the internal functioning of artificial neural networks is largely a mystery.
It is likely that the student will make a major contribution to both quantum theory and artificial intelligence by exploring, developing, and analysing neural networks that process spectroscopic data. This project is a collaboration with ETH Zurich (Prof Gunnar Jeschke) and Weizmann Institute (Prof Daniella Goldfarb), and will involve visits to both of these institutions.
Details
This is a 4-year studentship; it is open to UK and EU nationals, and includes all applicable university fees, as well as a tax-free stipend of £15,009 per year.
Due to funding restrictions this position is only open to UK students and EU students who meet the RCUK eligibility criteria
Application process
Applications for a PhD in Chemistry should be submitted online at https://studentrecords.soton.ac.uk/BNNRPROD/bzsksrch.P_Search
Please ensure you select the academic session 2019-20 when making your application in the academic year field and click on the Research radio button. Enter Chemistry in the search text field
Informal enquiries should be sent to Ilya Kuprov ( i.kuprov@soton.ac.uk ).
Any queries on the application process should be made to feps-pgr-apply@soton.ac.uk
The University of Southampton and the School of Chemistry both hold Athena SWAN Silver Awards, reflecting their commitment to equality, diversity and inclusion, and particularly to gender equality.
Company
Global Academy Jobs works with over 250 universities worldwide to promote academic mobility and international research collaboration. Global problems need international solutions. Our jobs board and emails reach the academics and researchers who can help.
"The globalisation of higher education continues apace, driving in turn the ongoing development of the global knowledge economy, striving for solutions to the world’s problems and educating a next generation of leaders and contributors."
Company info
You need to sign in or create an account to save a job.
Get job alerts
Create a job alert and receive personalized job recommendations straight to your inbox.
Create alert