id: NDk1NDIxMCA3

reference: 4954210

documentId: 4954210

connectionPointId: 7

lastModificationDate: 1551707250603

stillingsbetegnelse: PhD in Deep Learning for Optimizing Magnets

jobbeskrivelse:

Neural networks (NNs) are today used for everything from image/text recognition to robotics. However, we have just scratched the surface of using neural networks for tasks where they need to be truly creative. In this project, we essentially want to train a neural networks in physics and ask it to be creative with solutions to physical problems. To limit the problem in scope, we will focus on magnetism and investigate whether we can train a neural network to optimizing a structure of permanent magnets, such that this produces a required magnetic field. If this is possible, we may be able to open up a new area of research where creative artificial intelligence (AI) is used for making novel designs rather than using traditional and tedious optimization algorithms while at the same time clearing the path for designs and solutions hitherto un-thought of by humans.

This will have a huge impact not only on magnet design, but also on any other design problem where simple fundamental building blocks combine to a complex solution. The PhD project will be focused on applying an existing numerical model of magnetostatics for training NNs, using these for predictions and then go for inverting the NNs in order to get novel/creative solutions to permanent magnet optimization challenges.

This PhD position at DTU Energy is a part of a unique research project called AiMADE (http://www.aimade.org/) where we exploit artificial intelligence to discover and optimize materials for energy technologies. We will study the use of neural networks for optimizing permanent magnet structures by realizing a novel and fast computational model build on an existing computational framework for magnetic field calculations.

Responsibilities and tasks

Your role as a PhD student will be to investigate the possibility of training neural networks, or other AI-related approaches, on various magnet configurations modelled with our in-house code. Once trained and the system has reached an acceptable level of recognizing hitherto unseen structures for their key-properties (field magnitude, homogeneity etc.) you will work on inverting the system in order to reach predictive capability. You will be asking the neural network how a magnet configuration should look like when specifying a certain goal. You will be working together with other PhD students that also use this code / framework for other magnetism related problems and will thus from the beginning of the project enter into a group of young people with similar interests and technical challenges.

Qualifications


Candidates should have a two-year master's degree (120 ECTS points) or a similar degree with an academic level equivalent to a two-year master's degree, preferably in physics, computer science, engineering or another natural science-related discipline.

Further qualifications:

• Good communication skills in English
• Being able to work independently and in a team

Candidates with the following qualifications are preferred

• Experience with artificial intelligence
• Strong mathematical background, in particular with optimization
• Experience with magnetism or electromagnetism
• Experience with high performance computing
• Experience with Python, Fortran, Matlab or similar languages
• Experience with numerical modelling

Approval and Enrolment


The scholarship for the PhD degree is subject to academic approval, and the candidate will be enrolled in one of the general degree programmes at DTU. For information about our enrolment requirements and the general planning of the PhD study programme, please see the DTU PhD Guide. http://www.dtu.dk/english/Education/PhD/Rules/PhDguide

Salary and appointment terms


The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The period of employment is 3 years.

You can read more about career paths at DTU here. http://www.dtu.dk/english/about/job-and-career/working-at-dtu/career-paths

The expected starting date is March 2019 or thereafter.

The main activity will take place at the Department of Energy Conversion and Storage at DTU Risø campus initially and from ultimo 2019 at DTU Lyngby campus, as the department is being united at this campus.

Further information

Please contact Associate Professor Kaspar K. Nielsen, kaki (at) dtu.dk, Associate Professor Rasmus Bjørk, rabj (at) dtu.dk or Associate Professor Peter Stanley Jørgensen, psjq (at) dtu.dk, for further information.

Please do not send applications to this e-mail address, instead apply online as described below.

Application


Please submit your online application no later than 18 March 2019 (local time).

Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply online", fill out the online application form, and attach all your materials in English in one PDF file. The file must include:

• A letter motivating the application (cover letter)
• Curriculum vitae
• Grade transcripts and BSc/MSc diploma
• Excel sheet with translation of grades to the Danish grading system (see guidelines and Excel spreadsheet here) http://www.dtu.dk/english/Education/phd/Applicant/Pre_acceptance-1-

Candidates may apply prior to obtaining their master's degree but cannot begin before having received it.

Applications and enclosures received after the deadline will not be considered.

All interested candidates irrespective of age, gender, race, disability, religion or ethnic background are encouraged to apply.

DTU Energy is focusing on functional materials and their application in sustainable energy technology. Our research areas include fuel cells, electrolysis, solar cells, magnetic refrigeration, superconductivity and thermoelectrics. Additional information about the department can be found on http://www.ecs.dtu.dk http://www.ecs.dtu.dk

DTU is a technical university providing internationally leading research, education, innovation and scientific advice. Our staff of 6,000 advance science and technology to create innovative solutions that meet the demands of society, and our 11,200 students are being educated to address the technological challenges of the future. DTU is an independent academic university collaborating globally with business, industry, government and public agencies.


numberOfPosts: 1

jobCategoriesCodes_0: http://data.europa.eu/esco/isco/C2310

abstractJV_contact_0: Please apply using one of the specified channels

positionTypeCode: directhire

contractTypeCodes_0: fulltime

Arbejdsgiver Navn: Danmarks Tekniske Universitet

source: DK-STAR