Efficient Evolution for Intelligent Autonomous Systems

Qualification: PhD

Department: School of Informatics

Application deadline: 21st November 2019

Start date: 28th September 2020

Overview

Supervisors

Dr Jan Oliver Ringert and Dr Ivan Tyukin

Project Description:

Intelligent software is pervading the world around us. It is the driving enabler for innovations and products from autonomous vehicles, to enhanced health care, to efficient crisis response, to simple things like recommending the right movie for inspiration. However, often Artificial Intelligence (AI) does not deliver services alone but is embedded inside a larger software system. 

With increasing shifts towards AI we see new challenges in the construction and evolution of software systems. AI components are often not easily adapted and changing interfaces might mean costly retraining or synthesizing of the software. This might require the augmentation or creation of new datasets and specifications. 
This project will investigate how evolution can be efficiently supported for intelligent software systems. As an example, as part of the software of a self-driving car we might have an AI component that detects pedestrians, cyclists, and traffic lights. A software evolution step might change component interfaces to detecting dangers instead of the previously more detailed classification. Here the creation of new training data and costly retraining might not be necessary if we can compose the existing AI component with one that extracts dangers from classified objects.

This project will suggest suitable adaptations both on the software architecture level and on the AI level to make evolution more efficient. It is expected that this holistic view will be able to leverage techniques from software architecture and from AI that complement each other to provide timely answers to existing and emerging software evolution challenges.

The research will be evaluated in the context of autonomous vehicles in urban environments (see the school’s project DriverLeics https://ringert.blogspot.com/search/label/DriverLeics)  and on a drone for search and rescue missions (another project of the school). We are building links with industrial partners in the area of autonomous driving and robotics to apply our research.

References:

An overview of evolution of software models; and a look at software architectures and their evolution (by the first supervisor):

1. S. Maoz, J. O. Ringert: A framework for relating syntactic and semantic model differences. Software and System Modeling 17(3): 753-777 (2018) https://doi.org/10.1007/s10270-016-0552-y 

2. V. Bertram, S. Maoz, J. O. Ringert, B. Rumpe, M. von Wenckstern: Component and Connector Views in Practice: An Experience Report. MoDELS 2017: 167-177 https://doi.org/10.1109/MODELS.2017.29 

Techniques for adapting and correcting artificial intelligence components (by the second supervisor):

3. I. Tyukin, A.N. Gorban, S. Green, D. Prokhorov. Fast Construction of Correcting Ensembles for Legacy Artificial Intelligence Systems: Algorithms and a Case Study, Information Sciences (accepted). 2018. https://arxiv.org/abs/1810.05593.

4. I.Tyukin, A.N. Gorban, K. Sofeikov, I. Romanenko. Knowledge Transfer Between Artificial Intelligence Systems. Frontiers in Neurorobotics, 2018. doi:10.3389/fnbot.2018.00049.  https://arxiv.org/abs/1709.01547

Funding

Funding

UK/EU applicants

This research project is eligible for a fully funded College of Science and Engineering studentship which includes:

A full UK/EU fee waiver for 3.5 years
An annual tax free stipend (For 2019/20 this is currently £15,009)
Research Training Support Grant (RTSG)

International Applicants

This project is eligible for a partially funded College of Science and Engineering studentship which includes:

A full UK/EU fee waiver for 3.5 years (applicants will need to provide evidence they can fund the difference between the UK/EU fee and International fee for the duration of their studies)
An annual tax free stipend of £15,009 (2019/20)
Research Training Support Grant (RTSG)

Entry requirements

Entry requirements

Applicants are required to hold/or expect to obtain a UK Bachelor Degree 2:1 or better in a relevant subject or overseas equivalent.
The University of Leicester English language requirements apply where applicable.

Informal enquiries

Informal enquiries

Project / Funding Enquiries: csepgr@le.ac.uk 
Application enquiries to pgradmissions@le.ac.uk

How to apply

How to apply

Please use the Apply button at the bottom of the page.
Select September 2020 entry.

Application Notes

We recommend you apply as early as possible so that any missing information can be obtained before the deadline.

In the funding section of the form state CSE2020 Ringert Studentship

In the research proposal section include the name of the supervisors and project title.  If you are applying for more than one project within Informatics include details of each project.

In the personal statement section upload your completed CSE Studentship Form.  If you are applying for more than one Informatics project complete a form for each project and email the additional forms to csepgr@le.ac.uk together with your application ID number.  If you are applying for projects in other subject areas please submit separate PhD applications online.

Upload a copy of your CV, copies of your degree certificates and transcripts if awarded and evidence of English language proficiency if applicable and available.

If you already have reference letters please upload these. If not enter the contact details of your referees in the reference section. Please ask your referees if they can submit their references as quickly as possible, ideally within two weeks of receipt of our reference request.

Application timetable

21st November Deadline for applications and all supporting documents 
9th December Interview invitations to be sent out by email
w/c 13th January 2020  Interviews
21st January 2020 Informal offers to be made
31st January 2020 Deadline for acceptable of informal offers 

The PGR Admissions Office will notify unsuccessful applicants once a decision has been made

Eligibility

Eligibility

UK/EU applicants

International applicants who can demonstrate that they can fund the difference between UK/EU and International fees.