University of Hong Kong Featured PhD Programmes
University of West London Featured PhD Programmes
University of Hull Featured PhD Programmes

Evolving Ethical Deep Neural Networks [CDT-AIMLAC Studentship]


Cardiff School of Computer Science & Informatics

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
Prof Roger Whitaker , Dr L Turner No more applications being accepted Competition Funded PhD Project (Students Worldwide)

About the Project

AI is often trained to make decisions which can potentially adversely affect humans. For example, a self-driving car may be forced to crash in an unfamiliar scenario (aligned to “the trolley problem”) or a recommender system may (de-)prioritise an applicant CV for a role based on its perception of the person’s suitability. Because AI lacks human context, and because it may be trained on specific scenarios, it cannot be assured that ethical issues will be suitably handled without explicit consideration. Therefore, this project will look at the problem of evolving ethical AI. It will focus on using one of a range of techniques (neural evolution, generative adversarial networks) through which a neural network can become intrinsically structured to “do the right thing”. This project can be embedded in supervised learning, deep reinforcement learning (evolutionary AI such as evolution strategies), unsupervised learning or artificial life (ALIFE) simulation

(e.g., bibites https://www.youtube.com/watch?v=myJ7YOZGkv0&t=275s).

 The work will be developed in collaboration with IBM and other interested stakeholders. This PhD is suitable for someone keen to gain in-depth knowledge of state-of-the-art deep reinforcement learning through evolutionary processes or applying recent techniques such as adversarial AI. There is significant scope for technical creativity and experimentation, as well as engagement with a wide range of stakeholders.

 Eligibility 

The scholarships are open to UK/home and international candidates. For more information on eligibility, please visit the UKRI CDT in Artificial Intelligence, Machine Learning & Advanced Computing website

Entry Requirements

A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Candidates should be interested in AI and big data challenges, and in the research theme - novel mathematical, physical and computer science approaches.

Applicants whose first language is not English must demonstrate their proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component. (https://www.cardiff.ac.uk/study/international/english-language-requirements)

Applications

Please visit the CDT website http://cdt-aimlac.org/ and follow the instructions.

 Applicants should apply for postgraduate study via the Cardiff University webpage: https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/computer-science-and-informatics,

Select the programme Doctor of Philosophy in Computer Science & Informatics with a start date of 1st October 2021, and upload these documents with your application:

• your CV

• a personal statement/covering letter

• two reference letters

• current academic transcripts

In the research proposal section of your application, please specify the project title and supervisors of this project. If you are applying for more than one project, please list the individual titles of the projects in the text box provided. In the funding section, please select ’I will be applying for a scholarship/grant’.

To complete your application please email a pdf(s) of your application to [Email Address Removed]


Funding Notes

The UK Research and Innovation (UKRI) fully-funded scholarships cover the full cost of tuition fees, a UKRI standard stipend of £15,609 per annum (2021/22 rate) with additional funding for training, research and conference expenses. The scholarships are open to UK/home and international candidates. For general enquiries, please contact Rhian Melita Morris: [Email Address Removed]


FindAPhD. Copyright 2005-2021
All rights reserved.