[agents] Fully funded PhD student in Computing Science with focus on responsible machine learning

[Dignum, Virginia]

(Please distribute to interested candidates:)

PhD student in Computing Science with focus on responsible machine 
learning at Umeå University, Sweden

Is this interesting for you? Welcome with your application before 
October 17, 2022.

More information and application: 
https://umu.varbi.com/en/what:job/jobID:544187/


Project description

Learning with multiple representation (LMR) refers to machine learning 
methods that leverage several representations of the data and models or 
several formalizations of the learning task simultaneously, orchestrate 
them in a coordinated fashion, and use them in a synergistic way to 
solve a single problem. Multiple representations can interact in 
different ways and exchange information at various levels (e.g., data, 
model, prediction) and stages of the learning process. For example, an 
LMR system may have a parallel architecture, meaning that learning is 
essentially carried out in parallel (independently of each other), and 
predictions are only fused in the very end. However, these methods lack 
integration of responsible AI in terms of traceability of socio-ethical 
requirements, constraints, bias, fairness, transparency, and 
interoperability in designing and deploying frameworks in real-time AI 
systems.

This project aims to investigate, develop and integrate responsible AI 
framework with learning from multiple representations by taking 
advantage of the complementarity, the redundancy, and specific 
characteristics of different representations. LMR seeks to improve 
performance as well as ensure responsible learning from multiple 
representations in comparison to methods operating on a single 
representation only. Typical examples of LMR include the combination of 
numerical and symbolic formalisms, the representation of data and models 
on different levels of abstraction, and the combination of different 
types of supervision of the learner. Hence, this project plans to 
design, develop and evaluate novel methods and metrics that evaluate the 
trade-offs between computational and ethical requirements, and further 
analyses the bias, inclusion, transparency, and interpretability of LMR 
algorithms when deploying in real-time AI systems.

The successful candidate will contribute to the Social and Ethical 
Artificial Intelligence group and Autonomous Distributed Systems group 
at the Department of Computing Science within, collaborating with 
researchers in, e.g., machine learning, mathematical statistics, 
optimization, responsible AI or social AI.

This position is a part the European project LEMUR (Learning with 
Multiple Representations) funded by Horizon-MSCA-DN (MARIE 
Skłodowska-CURIE ACTIONS). The objective of MSCA Doctoral Networks is to 
implement doctoral programmes by partnerships of organisations from 
different sectors across Europe and beyond to train highly skilled 
doctoral candidates, stimulate their creativity, enhance their 
innovation capacities and boost their employability in the long-term.


-- 

Best regards/ Med vänlig hälsning,

*Prof. Dr. **Virginia Dignum*

Wallenberg Chair, Professor Responsible Artificial Intelligence

Program Director WASP-HS <wasp-hs.org>

*Umeå**University – Department of Computing Science*

*Tel:*  (work) +46 90 786 6308; (mobile) +46720 850 890*
Email:* virginia at cs.umu.se <mailto:virginia at cs.umu.se> / 
virginia.dignum at umu.se <mailto:virginia.dignum at umu.se>*
URL: *https://www.umu.se/en/staff/virginia-dignum/
*Twitter: *https://twitter.com/vdignum <https://twitter.com/vdignum>*
LinkedIn:*https://www.linkedin.com/in/vdignum/

Author of “Responsible Artificial 
Intelligence”:https://www.springer.com/gp/book/9783030303709
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cs.umbc.edu/pipermail/agents/attachments/20220923/53def3d2/attachment-0001.html>