Deep component analysis: algorithms and applications
File(s)
Author(s)
Trigeorgis, George
Type
Thesis
Abstract
Component Analysis (CA) methods have been crucial contributors for the large success
of machine learning over the past decades. Although predominately all CA methods are
linear models, depending on the formulation of the optimisation problem one can derive
vastly different results tailored to different tasks. Such linear methods have the natural
advantage of intepretability as they can easily be reasoned about, but also they are easy
to fit onto the available data. Unfortunately, as they are mostly linear models they can
not describe complex data distributions such as in-the-wild images of faces or, videos,
or even auditory signals. On the other hand deep learning methodologies have excelled
in modelling highly non-linear relations between highly heterogenious data distributions.
Nonetheless, they were mostly used as black-boxes and usually required orders of magnitude
more training samples than their linear counterparts to achieve similar performance.
In this thesis we will aim to combine the best of both worlds. That is to incorporate
the power of neural networks with the statistical intuition and the specially crafted ideas of
component analysis methods. The result methodologies will have a diverse application set,
solving problems from the areas of face clustering, timeseries alignment, domain adaptation,
and face alignment in a mainly unsupervised way.
of machine learning over the past decades. Although predominately all CA methods are
linear models, depending on the formulation of the optimisation problem one can derive
vastly different results tailored to different tasks. Such linear methods have the natural
advantage of intepretability as they can easily be reasoned about, but also they are easy
to fit onto the available data. Unfortunately, as they are mostly linear models they can
not describe complex data distributions such as in-the-wild images of faces or, videos,
or even auditory signals. On the other hand deep learning methodologies have excelled
in modelling highly non-linear relations between highly heterogenious data distributions.
Nonetheless, they were mostly used as black-boxes and usually required orders of magnitude
more training samples than their linear counterparts to achieve similar performance.
In this thesis we will aim to combine the best of both worlds. That is to incorporate
the power of neural networks with the statistical intuition and the specially crafted ideas of
component analysis methods. The result methodologies will have a diverse application set,
solving problems from the areas of face clustering, timeseries alignment, domain adaptation,
and face alignment in a mainly unsupervised way.
Version
Open Access
Date Issued
2017-10
Date Awarded
2018-03
Copyright Statement
Attribution NoDerivatives 4.0 International Licence (CC BY-ND)
Advisor
Zafeiriou, Stefanos
Schuller, Bjoern
Sponsor
Engineering and Physical Sciences Research Council
Google (Firm)
Publisher Department
Computing
Publisher Institution
Imperial College London
Qualification Level
Doctoral
Qualification Name
Doctor of Philosophy (PhD)