This advert is not available!
Deep neural networks have achieved outstanding success on prediction tasks in a supervised learning setting when enough labeled data is available. Yet, current AI systems are limited in their ability to understand the world around us, as shown in a limited ability to transfer and generalize between tasks.
In order to achieve the goal of designing and understanding intelligent machines, a key requirement is the ability to build latent generative models and learn from interventions and counterfactuals. This corresponds to an interactive learning environment, where the agent can discover causal factors through interventions, observe their effects and assign credit to each of its actions.
The goal of this position is thus to investigate how one can learn causal models of data from a reasonable set of assumptions as well as the experimental design of performing interventions and acquiring interventional data efficiently.
In this project, you will be involved in state-of-the-art machine learning research from the beginning and provide you with an opportunity to get started immediately with your topic. Our group is one of the few worldwide that successfully combines causality and deep learning with downstream applications from robotics to healthcare.
Our research is driven by real-world challenges with the potential for high societal impact and our work covers a wide spectrum between theory and application, with plenty of flexibility to adjust projects to your preferences. However, either a very strong theoretical background or experience with the common deep learning frameworks/software engineering skills is required.
Read more about what it is like to work at KTH
Requirements
Preferred qualifications
Great emphasis will be placed on personal competency
You will find contact information to trade union representatives at KTH's webbpage.
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:
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).
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.
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.
Type of employment | Temporary position |
---|---|
Contract type | Full time |
First day of employment | 1/4-22, or according to agreement |
Salary | Monthly |
Number of positions | 1 |
Full-time equivalent | 100% |
City | Stockholm |
County | Stockholms län |
Country | Sweden |
Reference number | J-2022-0594 |
Contact |
|
Published | 04.Mar.2022 |
Last application date | 04.Apr.2022 11:59 PM CEST |