Aiden Durrant
YOU?
Author Swipe
View article: EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks
EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks Open
Learning self-supervised representations that are invariant and equivariant to transformations is crucial for advancing beyond traditional visual classification tasks. However, many methods rely on predictor architectures to encode equivar…
View article: Linking small- and large-scale Digital Twins: A concept 
Linking small- and large-scale Digital Twins: A concept  Open
A Digital Twin (DT) is a data-driven model of a physical entity with two-information flows that enables the direct interaction between both. DTs of the natural environment are typically constructed by fusing multi-modal measurements of som…
View article: Monkey Transfer Learning Can Improve Human Pose Estimation
Monkey Transfer Learning Can Improve Human Pose Estimation Open
In this study, we investigated whether transfer learning from macaque monkeys could improve human pose estimation. Current state-of-the-art pose estimation techniques, often employing deep neural networks, can match human annotation in non…
View article: Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning
Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning Open
Pruning of deep neural networks has been an effective technique for reducing model size while preserving most of the performance of dense networks, crucial for deploying models on memory and power-constrained devices. While recent sparse l…
View article: Capsule Network Projectors are Equivariant and Invariant Learners
Capsule Network Projectors are Equivariant and Invariant Learners Open
Learning invariant representations has been the long-standing approach to self-supervised learning. However, recently progress has been made in preserving equivariant properties in representations, yet do so with highly prescribed architec…
View article: Automated Crevasse Mapping Using Deep Learning Foundation Models to Analyse Climate Change and Glaciology 
Automated Crevasse Mapping Using Deep Learning Foundation Models to Analyse Climate Change and Glaciology  Open
Climate change poses a significant global challenge, with its effects manifesting prominently through melting and retreating glaciers in the Arctic and Antarctic. Understanding the dynamics of glacier flow is imperative for predicting the …
View article: S-JEA: Stacked Joint Embedding Architectures for Self-Supervised Visual Representation Learning
S-JEA: Stacked Joint Embedding Architectures for Self-Supervised Visual Representation Learning Open
The recent emergence of Self-Supervised Learning (SSL) as a fundamental paradigm for learning image representations has, and continues to, demonstrate high empirical success in a variety of tasks. However, most SSL approaches fail to learn…
View article: HMSN: Hyperbolic Self-Supervised Learning by Clustering with Ideal Prototypes
HMSN: Hyperbolic Self-Supervised Learning by Clustering with Ideal Prototypes Open
Hyperbolic manifolds for visual representation learning allow for effective learning of semantic class hierarchies by naturally embedding tree-like structures with low distortion within a low-dimensional representation space. The highly se…
View article: Decarbonising our food systems: contextualising digitalisation for net zero
Decarbonising our food systems: contextualising digitalisation for net zero Open
The food system is undergoing a digital transformation that connects local and global supply chains to address economic, environmental, and societal drivers. Digitalisation enables firms to meet sustainable development goals (SDGs), addres…
View article: Deep learning techniques for in-core perturbation identification and localization of time-series nuclear plant measurements
Deep learning techniques for in-core perturbation identification and localization of time-series nuclear plant measurements Open
The use of machine learning in the field of reactor safety and noise diagnostics has recently seen great potential given the advancements made in computational tools, hardware and noise simulations. In this work we demonstrate how deep neu…
View article: Machine learning for analysis of real nuclear plant data in the frequency domain
Machine learning for analysis of real nuclear plant data in the frequency domain Open
Machine Learning is used in this paper for detecting anomalies in nuclear plant reactor cores. The proposed approach first generates large amounts of simulated data with different types of perturbations occurring at various locations in th…
View article: Hyperspherically regularized networks for self-supervision
Hyperspherically regularized networks for self-supervision Open
Acknowledgments This work used the Cirrus UK National Tier-2 HPC Service at EPCC (http://www.cirrus.ac.uk). Access granted through the project: ec173 - Next gen self-supervised learn- ing systems for vision tasks. Open access via Elsevier …
View article: Graph Neural Networks for Reservoir Level Forecasting and Draught Identification 
Graph Neural Networks for Reservoir Level Forecasting and Draught Identification  Open
<div> <p><span>The management of water resource systems is a longstanding and inherently complex problem, balancing an increasing number of interests to meet short- and long-term objectives sustainably. The difficulty of …
View article: Hyperspherically Regularized Networks for Self-Supervision
Hyperspherically Regularized Networks for Self-Supervision Open
Bootstrap Your Own Latent (BYOL) introduced an approach to self-supervised learning avoiding the contrastive paradigm and subsequently removing the computational burden of negative sampling associated with such methods. However, we empiric…
View article: Hyperspherically Regularized Networks for BYOL Improves Feature Uniformity and Separability.
Hyperspherically Regularized Networks for BYOL Improves Feature Uniformity and Separability. Open
Bootstrap Your Own Latent (BYOL) introduced an approach to self-supervised learning avoiding the contrastive paradigm and subsequently removing the computational burden of negative sampling. However, feature representations under this para…
View article: The Role of Cross-Silo Federated Learning in Facilitating Data Sharing in the Agri-Food Sector
The Role of Cross-Silo Federated Learning in Facilitating Data Sharing in the Agri-Food Sector Open
Data sharing remains a major hindering factor when it comes to adopting emerging AI technologies in general, but particularly in the agri-food sector. Protectiveness of data is natural in this setting; data is a precious commodity for data…
View article: Detection and localisation of multiple in-core perturbations with neutron noise-based self-supervised domain adaptation
Detection and localisation of multiple in-core perturbations with neutron noise-based self-supervised domain adaptation Open
Problem Case • We aim to unfold reactor transfer function to provide core diagnostics. • Derivation of core perturbation characteristics to classify and locate its origin. • Yet this is challenging due to the limited number of neutron dete…
View article: NEUTRON NOISE-BASED ANOMALY CLASSIFICATION AND LOCALIZATION USING MACHINE LEARNING
NEUTRON NOISE-BASED ANOMALY CLASSIFICATION AND LOCALIZATION USING MACHINE LEARNING Open
A methodology is proposed in this paper allowing the classification of anomalies and subsequently their possible localization in nuclear reactor cores during operation. The method relies on the monitoring of the neutron noise recorded by i…
View article: Neutron noise-based anomaly classification and localization using machine learning
Neutron noise-based anomaly classification and localization using machine learning Open
A methodology is proposed in this paper allowing the classification of anomalies and subsequently their possible localization in nuclear reactor cores during operation. The method relies on the monitoring of the neutron noise recorded by i…
View article: 3D Convolutional and Recurrent Neural Networks for Reactor Perturbation Unfolding Anomaly Detection
3D Convolutional and Recurrent Neural Networks for Reactor Perturbation Unfolding Anomaly Detection Open
Peer reviewed
View article: 3D convolutional and recurrent neural networks for reactor perturbation unfolding and anomaly detection
3D convolutional and recurrent neural networks for reactor perturbation unfolding and anomaly detection Open
With Europe's ageing fleet of nuclear reactors operating closer to their safety limits, the monitoring of such reactors through complex models has become of great interest to maintain a high level of availability and safety. Therefore, we …