The Hong Kong Polytechnic University Featured PhD Programmes
University College London Featured PhD Programmes
Birkbeck, University of London Featured PhD Programmes
University of Leeds Featured PhD Programmes
University of Leeds Featured PhD Programmes

Mathematics PhD Projects, Programs & Scholarships in Manchester

We have 22 Mathematics PhD Projects, Programs & Scholarships in Manchester

  • Mathematics×
  • United Kingdom×
  • Manchester×
  • clear all
Order by 
Showing 11 to 20 of 22
  Contextualised Multimedia Information Retrieval via Representation Learning
  Dr K Chen
Applications accepted all year round

Funding Type

PhD Type

Multimedia Information Retrieval (MIR) is an important research area in AI that aims at extracting semantic information from multimedia data sources including perceivable media such as audio, image and video, indirectly perceivable sources such as text, bio-signals as well as not perceivable sources such as bio-information, stock prices, etc.
  Information Component Analysis via Deep Learning
  Dr K Chen
Applications accepted all year round

Funding Type

PhD Type

As their prominent characteristics, perceptual data often convey the mixing information, which often results in the inadequate performance for a specific perceptual information processing task due to the interference of irrelevant information components.
  Deep Learning for Temporal Information Processing
  Dr K Chen
Applications accepted all year round

Funding Type

PhD Type

Temporal information process covers a broad class of learning problems where knowledge can be acquired from data of a sequential order, e.g.
  Problems in large graphs (e.g., social networks, VANETs)
  Dr R Sakellariou
Applications accepted all year round

Funding Type

PhD Type

A number of interesting problems nowadays can be modelled by large graphs. For example, web links constitute a graph (google and the pagerank algorithm exploit properties of this graph), also facebook friendships, paper citation patterns and many more.
  Ensemble Strategies for Semi-Supervised, Unsupervised and Transfer Learning
  Dr K Chen
Applications accepted all year round

Funding Type

PhD Type

Traditionally there are two main paradigms in machine learning, supervised vs. unsupervised learning.
  Zero-Shot Learning and Applications
  Dr K Chen
Applications accepted all year round

Funding Type

PhD Type

Zero-shot learning refers to a novel paradigm on learning how to recognise new concepts by just having a description of them. For example, zero-shot learning works on a setting of solving a classification problem when no labelled training examples are available for all classes, which are divided into two class subsets.
  Multi-task Learning and Applications
  Dr K Chen
Applications accepted all year round

Funding Type

PhD Type

In traditional machine learning, a learning system can be trained to deal with a specific single task, while human is able to complete multiple tasks with the same learning strategy.
  Automatic Activity Analysis, Detection and Recognition
  Dr K Chen
Applications accepted all year round

Funding Type

PhD Type

Activity detection, analysis and recognition are related to several important areas in machine perception research and applications.
  Biologically-Plausible Continual Learning
  Dr K Chen
Applications accepted all year round

Funding Type

PhD Type

Continual learning (aka lifelong learning) refers to a problem on how a learning system learns multiple tasks in succession over the lifespan where later tasks do not degrade the performance of the system learned for the earlier tasks and, ideally, the system can leverage the knowledge learned in previous tasks to facilitate learning the new tasks better.
  Machine learning to locate defects in ultrasonic inspection images
  Prof T Cootes, Dr M Fergie
Applications accepted all year round

Funding Type

PhD Type

It is important that manufactured components are inspected to identify defects which may cause early failure, particularly in safety critical systems.
Show 10 15 30 per page


FindAPhD. Copyright 2005-2019
All rights reserved.