2-year Postdoc in Brain-inspired Inhibition in Deep Learning for image analysis

Founded in 1614, the University of Groningen enjoys an international reputation as a dynamic and innovative institution of higher education offering high-quality teaching and research. Flexible study programmes and academic career opportunities in a wide variety of disciplines encourage the 36,000 students and researchers alike to develop their own individual talents. As one of the best research universities in Europe, the University of Groningen has joined forces with other top universities and networks worldwide to become a truly global centre of knowledge.

The selected candidate will be embedded in the group Information Systems, of the Computer Science department, Bernoulli Institute for Mathematics, Computer Science, and Artificial Intelligence, Faculty of Science and Engineering, University of Groningen.

One of the main challenges in learning algorithms for vision applications is the determination of computational models that can generalize beyond the training distribution and that are robust to adversarial attacks. This will be the focus of the two-year postdoc position.

The selected candidate will be enrolled with the Information Systems group, University of Groningen, and will collaborate with ongoing PhD students on the above-mentioned topic. The ideal candidate must have a solid foundation in developing deep learning architectures for vision applications and a proven record of publishing high-quality papers.

In this position the candidate will:

• investigate the embedding of brain-inspired inhibition components in various deep learning architectures for deep hashing (retrieval), classification and segmentation problems
• develop and evaluate methodologies of inhibition-augmented deep architectures
• collaborate with the 4 ongoing PhD projects working on first-person vision, medical, forensic and radio astronomy image analysis.

The objective of this temporary position is the production of a number of research articles in peer-reviewed scientific journals and conference proceedings.

The successful candidate should:

• have a keen interest in pursuing fundamental research in deep learning with a focus on brain-inspired methodologies
• have a PhD degree in computer science, artificial intelligence or another relevant field
• have proven experience in building deep learning architectures with Python for computer vision problems
• have proven track record in publishing high quality peer reviewed papers
• have excellent verbal and written communication skills in English
• possess good analytical skills and a positive attitude towards collaborating with PhD students.

We offer you, following the Collective Labour Agreement for Dutch Universities:

• a salary of € 2,960 gross per month in the first year, up to a maximum of € 4,670 gross per month (salary scale 10) in the fourth and final year for a full-time working week
• a holiday allowance of 8% gross annual income and an 8.3% year-end bonus
• a full-time position (1.0 FTE). The successful candidate will first be offered a temporary position of one year with the option of renewal for another one year. Prolongation of the contract is contingent on sufficient progress in the first year to indicate that a successful completion of the objectives within the next year is to be expected.

For information you can contact:

Dr George Azzopardi,   [email protected]

(please do not use the email addresses above for applications)