Jay Paul Morgan

Swansea University | SWAN

Deep Neural Networks (DNNs) have often supplied state-of-the-art results in pattern recognition tasks. Despite their advances, however, the existence of adversarial examples have caught the attention of the community. Many existing works have proposed methods for searching for adversarial examples within fixed-sized regions around training points....

In Computer Science there is a strong consensus that it is highly desirable to combine the versatility of Machine Learning (ML) with the assurances formal verification can provide. However, it is unclear what such ‘verified ML’ should look like. This paper is the first to formalise the concepts of classifiers and learners in ML in terms of computab...

The study and prediction of space weather entails the analysis of solar images showing structures of the Sun’s atmosphere. When imaged from the Earth’s ground, images may be polluted by terrestrial clouds which hinder the detection of solar structures. We propose a new method to remove cloud shadows, based on a U-Net architecture, and compare class...

The acoustic repertoires of long-finned pilot whales (Globicephala melas) in the Mediterranean Sea are poorly understood. This study aims to create a catalogue of calls, analyse acoustic parameters, and propose a classification tree for future research. An acoustic database was compiled using recordings from the Alboran Sea, Gulf of Lion and Liguri...

We explore different strategies to integrate prior domain knowledge into the design of graph neural networks (GNN). Our study is supported by a use-case of estimating the potential energy of chemical systems (molecules and crystals) represented as graphs. We integrate two elements of domain knowledge into the design of the GNN to constrain and regu...

The study and prediction of space weather entails the analysis of solar images showing structures of the Sun's atmosphere. When imaged from the Earth's ground, images may be polluted by terrestrial clouds which hinder the detection of solar structures. We propose a new method to remove cloud shadows, based on a U-Net architecture, and compare class...

We explore different strategies to integrate prior domain knowledge into the design of a deep neural network (DNN). We focus on graph neural networks (GNN), with a use case of estimating the potential energy of chemical systems (molecules and crystals) represented as graphs. We integrate two elements of domain knowledge into the design of the GNN t...

Machine Learning (ML) has been a transformative technology in society by automating otherwise difficult tasks such as image recognition and natural language understanding. The performance of Deep Learning (DL), in particular, has improved to the point where it can be applied to automotive vehicles – a situation in which trust is placed on the ML sy...

There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable analysis. This allows us to define the computational...

This paper presents a novel method to address legal rights for children through a chatbot framework by integrating machine learning, a dialogue graph, and information extraction. The method addresses a significant problem: we cannot presume that children have common knowledge about their rights or express themselves as an adult might. In our framew...