HAICu PhD: Deep Learning for Image Classification and Generation: New Discoveries with Little Data

HAICu PhD: Deep Learning for Image Classification and Generation: New Discoveries with Little Data

Published Deadline Location
29 Oct 1 Dec Tilburg

You cannot apply for this job anymore (deadline was 1 Dec 2024).

Browse the current job offers or choose an item in the top navigation above.

Tilburg School of Humanities and Digital Sciences in close collaboration with Naturalis Biodiversity Center has a job opening for:
HAICu PhD:
Deep Learning for Image Classification and Generation: New Discoveries with Little Data.

Job description

We are advertising a PhD position in the context of a large-scale national project:
HAICu: digital Humanities - Artificial Intelligence - Cultural heritage
This position is embedded in the Cognitive Science and AI department of Tilburg University in close collaboration with Naturalis Biodiversity Center.

The PhD project
Tilburg University and partners are seeking a candidate for a 4-year PhD position to investigate deep learning using sparse labels in cultural heritage data, as part of the national HAICu project. The project will be coordinated by Eric Postma (CSAI, Tilburg University), Anne Schulp (Naturalis/Utrecht University), and Dan Stowell (CSAI, Tilburg University/Naturalis). The project is interdisciplinary at the intersection of Deep Learning for Vision and Paleontology.

The focus of the PhD project will be on developing and evaluating existing and novel computer vision techniques for the automatic visual classification of paleontologic objects, i.e., fossil bones and bone fragments. Based on existing and newly acquired digitized data of bones and bone fragments, the PhD candidate will explore the latest AI algorithms for visual classification to overcome the main challenge: sparse data. For many bone fragments, only a few examples are available. Modern AI techniques can overcome such sparsity by imposing domain-specific constraints or by pretraining on related data. In addition, the candidate will explore generative algorithms to "auto-complete" bone fragments, offering context to the fossil discoveries by the citizen scientist community. 

The candidate will be asked to:

  • Develop a specific research proposal within the proposed theme
  • Review the academic literature relevant to the project’s goals
  • Carry out research, present your results, and author scientific articles on the above-mentioned topics
  • Collaborate with members of the project supervisors at Tilburg University, Naturalis, Utrecht University, and with the broader HAICu consortium, in particular with the other members of WP3 (see below)
  • Engage and collaborate with other researchers working on computer vision and paleontology research
  • Complete a PhD thesis written in English
  • Collaborate on outreach and public engagement activities
  • Gain teaching experience

Within the dynamic HAICu team, the PhD researcher will participate in Work Package 3 (WP3), entitled “Learning from sparse examples”. In this WP, we collaborate with AI and machine learning experts from University of Groningen, Fontys University of Applied Sciences, and many other partners from the HAICu-wide community.

The HAICu Project
The HAICu project is a large-scale Dutch research project by universities and cultural-heritage institutions into new forms of Artificial Intelligence-based access to multimodal Cultural-Heritage data, both contemporary and historical. Within HAICu, AI researchers, Digital Humanities researchers and a wide range of public and private partners will co-develop scientific solutions to unlock the true societal potential of the current heterogeneous digital heritage collections. It will provide easier, richer and more reliable data access to citizens, journalists, civic organisations, and various other stakeholders.

HAICu is funded by the NWO National Science Agenda (NWA) and has a budget of about EUR 10 million. HAICu started in January 2024 and will last 6 years (until Jan 2030).

For more information about HAICu, please see https://www.haicu.science/

Specifications

Tilburg University

Requirements

  • A Master’s degree in artificial intelligence, computer science, computer vision, or related area
  • Demonstrated skills in machine learning
  • Experience with training and/or designing neural networks for computer vision tasks is strongly desired
  • Interest in or affinity with paleontology is a plus
  • Excellent communication and academic writing skills in English
  • Reading skills in Dutch are a plus, given that most relevant data is in Dutch
  • Team player mindset and aptitude for interdisciplinary research

Conditions of employment

  • This is a position for 1.0 FTE (40 hours per week) of full working hours. Working hours can be flexible for caring responsibilities. This is a vacancy for a temporary position in accordance with Article 2.3, paragraph 5 of the CLA for Dutch Universities. You will be given a temporary employment contract for the duration of 1 year. Upon positive outcome of the first-year evaluation, you will receive a subsequent employment contract that will be extended for an additional 3 years. Tilburg University offers excellent employment conditions with attention to flexibility and (personal) development and attractive fringe benefits. 
  • The salary amounts to €2.872 in de first year of the PhD, and will increase to €3.670 in the fourth year of the PhD (gross per month for full-time employment), based on UFO profile PhD and salary scale PhD of the Collective Labour Agreement for Dutch Universities
  • You are entitled to a vacation allowance of 8% and a year-end bonus of 8.3% of your gross annual income. If you work 40 hours per week, you will receive 41 paid days of leave per year. All employees of the university are covered by the so-called General Pension Fund for Public Employers (Stichting Pensioenfonds ABP).  
  • We make clear agreements about career paths and offer all kinds of facilities and arrangement to maintain an optimal balance between work and private life. You can also follow numerous training courses, for example, in the areas of leadership skills, personal effectiveness, and career development. 
  • Tilburg University values an open and inclusive culture. We embrace diversity and encourage the mutual integration of groups of employees and students. We focus on creating equal opportunities for all our employees and students so that everyone feels at home in our university community. 
  • Tilburg University has a lively campus in beautiful green surroundings that is easily accessible by public transport. We are committed to a sustainable society and challenge you to make an active contribution.
  • Please visit working at Tilburg University for more information on our terms of employment. 

Employer

Tilburg School of Humanities and Digital Sciences

Research and education at the Tilburg School of Humanities and Digital Sciences (TSHD) has a unique focus on humans in the context of the globalizing digital society, on the development of artificial intelligence and interactive technologies, on their impact on communication, culture and society, and on moral and existential challenges that arise. The School of Humanities and Digital Sciences consists of four departments: Communication and Cognition, Cognitive Science and Artificial Intelligence, Culture Studies and Philosophy; several research institutes and a faculty office. Also the University College Tilburg is part of the School. Each year around 275 students commence a Bachelor or (Pre) Master Program. The School has approximately 2000 students and 250 employees.
Tilburg School of Humanities and Digital Sciences

Specifications

  • PhD
  • Language and culture; Behaviour and society; Engineering
  • max. 40 hours per week
  • €2872—€3670 per month
  • University graduate
  • 22517

Employer

Location

Warandelaan 2, 5037 AB, Tilburg

View on Google Maps

Interesting for you