UiB University of Bergen, Norway - Logo

PhD position in Computer Science – HUGIN-MUNIN project, Norway

University of Bergen (UiB)

Norway

PhD position  in  HUGIN-MUNIN project, Ostfold University – Norway, Oct 2021

Support us by Sharing!

ADVERTISEMENT
Scroll Down for Content

General Info

Position: PhD
No. of Positions: 1
Research Field: , , , ,
Deadline to Apply: Expired
Joining Date: -
Contract Period: 3 Years
Salary: According to Standard Norms

Workplace:
-
Department of Computer Science & Communication
University of Bergen (UiB)
Halden,

ADVERTISEMENT
Scroll Down for Content

Qualification Details

  • completed a Master’s degree or equivalent within the field of Computer/Electronics/Electrical Engineering, Computer Science, Computer Applications, Mathematics, Statistics or a closely related field.
  • the average grade point of courses should be B (for candidates with publications in reputed venues or with prior work experience, this might be relaxed).
  • hands-on experience with Popular Deep-learning Libraries/ Environments like Keras, Tensorflow, Pytorch.
  • fluent oral and written communication skills in English

Desired Criteria:

  • knowledge in Machine Learning, Computer Vision, Image Analysis
  • sound knowledge of advanced multi-variable Calculus, Linear Algebra, Statistics
  • very good programming skills in C/C++/Python
  • prior publications in top tier Journals /conferences on Machine Learning, Computer Vision in general (even better if precisely in Document Image Analysis)
  • knowledge of Shell scripting

Personal characteristics

  • interpersonal skills and a willingness to work as part of an international team based in Norway
  • organized and Self-motivated individual, eager to work with industry partners and colleagues on research problems

Emphasis will be placed on the following:

  • prior academic and/or research performance
  • prior relevant work experience (if applicable)
  • the applicant’s own ideas of research themes and research design that would be relevant for the project proposal.

Responsibilities/Job Description

Within the project, the PhD candidate will work mainly in the following areas:

Zero-shot word recognition and spotting (out-of-lexicon word spotting) by proposing novel methods pertinent to Norwegian handwritten texts. To develop GAN-based methods to emulate handwritten text on the basis of specific writer styles and also generic handwriting styles representing a specific time period. These could be used to synthetically generate  texts for training purposes and  to Fine-tune the base GAN model on specific handwriting.The successful candidate will be a member of an active research group at Østfold University College. The candidate is expected to do research, develop prototype implementations and write research papers on the topic of the project. Research visits to different relevant research groups in European countries will also be possible on availability of funds and opportunity.

How to Apply?

Online Application through "Apply Now" Button from this page or from advertisement webpage (URL below)

Reference Number: -
(If any, use it in the necessary place)

ADVERTISEMENT
Scroll Down for Content

Documents Required

Application must include the following:

  • Letter of intent (2 pages) that includes your qualification, skills and motivation and applicant’s own ideas of research themesand research design that would be relevant for the project.
  • A curriculum vitae
  • List of publications (if applicable). Include a short description of your contribution in multi-authored publications.
  • Copies of degree certificates and transcripts of academic records (all certified and translated to English if not awarded in the Scandinavian region)

All attachments should be included electronically within the application deadline. The faculty may require further documentation, e.g. proof of claimed English proficiency.

About the Position

The Ph.D. position is a full time (100%) fixed term position for 3 years, and is fully funded by The Research Council of Norway under funding scheme “Collaborative Project on Digital Security and Artificial Intelligence, Robotics and Autonomous Systems".  Østfold University College is the project leader in the project. Main place of work will be at our campus in Halden, but some presence at our campus in Fredrikstad may be expected.

Project title: Enhanced Access to Norwegian Cultural Heritage using AI-driven Handwriting Recognition (Hugin-Munin)

Project description:The overall aim of the HUGIN-MUNIN project is to develop technological solutions that will enable the use of Handwritten Text Recognition (HTR) without the requirements for massive manual annotation and model training. The solutions developed will go beyond traditional supervised  machine learning by using ideas from active learning, unsupervised learning, transfer learning, and zero-shot learning. It will also leverage natural language processing resources recently developed for the Norwegian language.

The project will significantly increase the scope and variety of sources available for data-driven research on Norwegian culture and society. It will also democratize the access to knowledge by enabling the public to read documents that have so far been mainly reserved for domain experts and scholars. The Ph.D student is expected to collaborate with other consortium members in the project which includes National Library of Norway (the digitization hub for the entire country), along with Lumex AS from Norway and another technology partner Teklia from France both internationally recognized organizations on developing handwritten text recognition systems.

About the Employer: University of Bergen (UiB)

Note or Other details

For more information about Østfold University College, visit our website at https://www.hiof.no/english/

ADVERTISEMENT
Scroll Down for Content

Contact details

For further information about the project, please contact the project leader. For other information, please contact Human Resources or the Dean of The Faculty.

Advertisement Details: Phd position – Applied Machine Learning for Historical Document Image Analysis

Other Vacancies from this field

ADVERTISEMENT
Scroll Down for Content

Support us by Sharing!