Imperial College London Featured PhD Programmes
University of Southampton Featured PhD Programmes
University of Oxford Featured PhD Programmes
University of Southampton Featured PhD Programmes
University of East Anglia Featured PhD Programmes

Deep Feature Selection of Multi-Modal Data (CO/CG/-Un5/2020)

  • Full or part time
  • Application Deadline
    Sunday, August 02, 2020
  • Self-Funded PhD Students Only
    Self-Funded PhD Students Only

Project Description

Feature selection aims to eliminate redundant and irrelevant features via different criteria. The most commonly used criteria measure the relevance of each feature to the desired output, and use this information to select the most important features. Eliminating irrelevant and redundant features, results in a permanent reduction in the dimensionality of the data, and this can increase the processing speed and accuracy of the utilised machine learning methods.

Feature selection using Deep Neural Networks has not been well studied, despite its importance which facilitates understanding of data. Projects under this topic concern the development of algorithms which are capable of removing irrelevant features from large uni-modal and multi-modal datasets. Projects include detection and analysis of anomalous data in various environments such as smart environments, information retrieval, and biomedical applications.

Start date: January 2020, April 2020, July 2020, October 2020.

Entry requirements:

Applicants should have, or expect to achieve, at least a 2:1 Honours degree (or equivalent) in Computer Science with a strong interest in Artificial Intelligence and data-science. Applicants must be competent in programming and applied mathematics, and should have a strong ability to write computer programs preferably in the Python programming language. An MSc in Artificial Intelligence and/or Data Science is highly desirable.

How to apply:

All applications are made online, please select the school/department name under the programme name section and include the quote reference number.

Funding Notes

This is an open call for candidates who are sponsored or who have their own funding. If you do not have funding, you may still apply, however Institutional funding is not guaranteed. Outstanding candidates (UK/EU/International) without funding will be considered for funding opportunities which may become available in the School.

Band RB (UK/EU: TBC; international: £22,350).


Taherkhani, A, Cosma, G, McGinnity, TM (2018) Deep-FS: A feature selection algorithm for Deep Boltzmann Machines, Neurocomputing, 322, pp.22-37, ISSN: 0925-2312.
DOI: 10.1016/j.neucom.2018.09.040.
Available from:

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.