Postdoc in Robust Learning of Probabilistic Deep Dynamic Models - Hiring in process/Finished, not possible to apply

Job description

The Division of Information Science and Engineering at the School of Electrical Engineering and Computer Science is currently recruiting one postdoc in Robust Learning of Probabilistic Deep Dynamic Models.

The goal of this project is to develop new principles and methods for dynamical systems modeling, based on neural networks. Deep neural networks can help to model complex probability distributions (e. g., variational autoencoders, generative adversarial models) that are explicit in nature, allowing us to compute the likelihood of data as well as sample distributions efficiently. The use of explicit distributions will also allow us to exploit Bayesian learning principles. Such dynamical systems can provide efficient detection / estimation / processing of the underlying signal of interest. In addition, the processing and learning will be robust to noise. To learn robust low-dimensional structures from dynamic data, we will consider deep networks that most discriminate between dynamic models. Information-theoretic measures and concepts borrowed from causal inference will help us further to improve such dynamic models. Principles and methods developed in this project will be advantageous for several applications. Examples include time-series of patient data that can help to predict infections, autonomous vehicle video data that can be used to forecast the intention of neighboring vehicles, and sports video data that can be analyzed to determine player location and action. In addition, we will explore additional applications in collaboration with other researchers at KTH and industry.

As a postdoc your primary goal is to progress toward becoming a fully independent researcher, both through own independent work and in collaboration with other researchers at the division. In this project, you will be supported by the Associate Professors Saikat Chatterjee, Ragnar Thobaben, and Markus Flierl who will provide you with opportunities to engage in on-going collaborations with industrial partners and the Karolinska University Hospital in Stockholm.

What we offer

• A position at a leading technical university that generates knowledge and skills for a sustainable future
• Engaged and ambitious colleagues along with a creative, international and dynamic working environment
• Works in Stockholm, in close proximity to nature
• Help to relocate and be settled in Sweden and at KTH

Read more about what it is like to work at KTH

Qualifications

Requirements

• A doctoral degree or an equivalent foreign degree, This eligibility requirement must be met no later than the time the employment decision is made.
• Demonstrated scientific excellence and outstanding academic track record.
• Demonstrated potential for future development.
• Strong background in deep learning including RNNs, Bayesian machine learning including linear dynamical systems, information-theoretic concepts for learning, and related programming skills including Python.
• Demonstrated analytical and problem-solving skills.
• Ability to work independently.
• Demonstrated excellent command of English orally and in writing as it is needed in the daily work.

Preferred qualifications

• A doctoral degree or an equivalent foreign degree, obtained within the last three years prior to the application deadline.
• Demonstrated collaboration skills.
• Demonstrated strong engagement with the international research community (e.g., contributions to public discussions, conference reviews, survey and tutorial material).
• Awareness of diversity and equal opportunity issues, with specific focus on gender equality.

Great emphasis will be placed on personal competency.

Trade union representatives

You will find contact information to trade union representatives at KTH's webbpage.

Application

Log into KTH's recruitment system in order to apply to this position. You are the main responsible to ensure that your application is complete according to the ad.

The application must include:

• CV including relevant professional experience and knowledge.
• Copy of diplomas and grades from your previous university studies. Translations into English or Swedish if the original documents have not been issued in any of these languages.
• Brief account of why you want to conduct research, your academic interests and how they relate to your previous studies and future goals. Max two pages long.

Your complete application must be received at KTH no later than the last day of application, midnight CET/CEST (Central European Time/Central European Summer Time).

About the employment

The position offered is for, at the most, two years.

A position as a postdoctoral fellow is a time-limited qualified appointment focusing mainly on research, intended as a first career step after a dissertation.

Others

Striving towards gender equality, diversity and equal conditions is both a question of quality for KTH and a given part of our values.

For information about processing of personal data in the recruitment process please read here.

We firmly decline all contact with staffing and recruitment agencies and job ad salespersons.

Disclaimer: In case of discrepancy between the Swedish original and the English translation of the job announcement, the Swedish version takes precedence.