Connectionists: Postdoctoral Research Associate Position in Deep Learning

[Timothy Hospedales]

Applications are invited for the position of Postdoctoral Research Associate in the EPSRC and DSTL funded UDRC Phase 3 project. This is a large project with several open positions, including one within the Machine Intelligence Group at the School of Informatics in the University of Edinburgh. 

The particular focus of this post is on certifying and verifying deep neural networks. As Deep Neural Networks (DNNs) are deployed in increasingly many and increasingly mission-critical applications, it becomes more important to be confident that their outputs can be relied upon for decision-making. This is a particularly salient concern when DNN-based systems are deployed and exposed to new, unexpected, and potentially adversarial inputs. The researcher will develop novel methods for certifying and verifying that DNNs are fit for purpose, even when extrapolating in the presence of novel inputs. Potential techniques to explore include both formal and meta-learning based approaches to increasing reliability to out of sample data, as well as explainable AI approaches to allow reasoning to be manually checked for validity. 

The competitive candidate will have a strong track record of publications in venues such as ICML, NIPS, ICLR, CVPR and ICCV.

This fixed-term post is available for a period of 2.5 years from January 2019. The closing date for applications is 04 October 2018. International applicants are welcome.

Further details and a link to the online application portal are available at https://www.vacancies.ed.ac.uk/pls/corehrrecruit/erq_jobspec_version_4.jobspec?p_id=045067.

Informal enquiries may be directed to Dr Timothy Hospedales at t.hospedales at ed.ac.uk.

---
Timothy Hospedales
Reader (Associate Professor)
School of Informatics,
University of Edinburgh
http://mig.inf.ed.ac.uk/


-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.