Incorporating prior knowledge into generative adversarial networks
Lead Research Organisation:
University of Bristol
Department Name: Engineering Mathematics and Technology
Abstract
In the last few years, we have seen several success stories regarding the application of machine learning to different tasks, e.g. deep learning for speech recognition, music processing or image classification. The accuracy of machines in such problems has improved dramatically. However, when the task at hand involves a deeper understanding, machine learning techniques are far behind humans.
The main concept of this thesis is to develop novel machine learning systems that by encoding expert knowledge are able to provide a deeper understanding of heterogeneous media and generalise to new contexts and application domains and to communicate the understanding of the signals to other systems, including humans.
This will mainly be applied to Generative Adversarial Networks which is a model that takes a training set, consisting of samples drawn from an underlying probability distribution, and learns to represent an estimate of that distribution somehow. The generative nature of these networks makes them ideal in order to encode prior knowledge, in a similar manner as one would in probabilistic graphical models.
The main concept of this thesis is to develop novel machine learning systems that by encoding expert knowledge are able to provide a deeper understanding of heterogeneous media and generalise to new contexts and application domains and to communicate the understanding of the signals to other systems, including humans.
This will mainly be applied to Generative Adversarial Networks which is a model that takes a training set, consisting of samples drawn from an underlying probability distribution, and learns to represent an estimate of that distribution somehow. The generative nature of these networks makes them ideal in order to encode prior knowledge, in a similar manner as one would in probabilistic graphical models.
Organisations
Publications
Hepburn A
(2020)
Enforcing perceptual consistency on Generative Adversarial Networks by using the Normalised Laplacian Pyramid Distance
in Proceedings of the Northern Lights Deep Learning Workshop
Hepburn A
(2018)
Album cover generation from genre tags
Hepburn A
(2018)
Proper losses for learning with example-dependent costs
Hepburn Alexander
(2019)
PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance
in arXiv e-prints
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/N509619/1 | 30/09/2016 | 29/09/2021 | |||
1940966 | Studentship | EP/N509619/1 | 30/09/2017 | 29/09/2021 | Alexander Hepburn |