94 citations · 125 across the 12 of their papers we have counts for
12 papers
Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head
Harry J Davies
Large Language Models (LLMs) typically have billions of parameters and are thus often difficult to interpret in their operation. In this work, we demonstrate that it is possible to…
Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models
Harry J. Davies, Giorgos Iacovides, Danilo P. Mandic
The sheer scale of data required to train modern large language models (LLMs) poses significant risks, as models are likely to gain knowledge of sensitive topics such as bio-securi…
In-ear ECG Signal Enhancement with Denoising Convolutional Autoencoders
Edoardo Occhipinti, Marek Zylinski, Harry J. Davies +5
The cardiac dipole has been shown to propagate to the ears, now a common site for consumer wearable electronics, enabling the recording of electrocardiogram (ECG) signals. However,…
Interpretable Pre-Trained Transformers for Heart Time-Series Data
Harry J. Davies, James Monsen, Danilo P. Mandic
Decoder-only transformers are the backbone of the popular generative pre-trained transformer (GPT) series of large language models. In this work, we employ this framework to the an…
A Deep Matched Filter For R-Peak Detection in Ear-ECG
Harry J. Davies, Ghena Hammour, Marek Zylinski +2
The Ear-ECG provides a continuous Lead I electrocardiogram (ECG) by measuring the potential difference related to heart activity using electrodes that can be embedded within earpho…
Amplitude-Independent Machine Learning for PPG through Visibility Graphs and Transfer Learning
Yuyang Miao, Harry J. Davies, Danilo P. Mandic
Photoplethysmography (PPG) refers to the measurement of variations in blood volume using light and is a feature of most wearable devices. The PPG signals provide insight into the b…
Hearables: Ear EEG Based Driver Fatigue Detection
Metin C. Yarici, Pierluigi Amadori, Harry Davies +4
Ear EEG based driver fatigue monitoring systems have the potential to provide a seamless, efficient, and feasibly deployable alternative to existing scalp EEG based systems, which…
Hearables: Feasibility of Recording Cardiac Rhythms from Single Ear Locations
Metin Yarici, Wilhelm Von Rosenberg, Ghena Hammour +5
Wearable technologies are envisaged to provide critical support to future healthcare systems. Hearables - devices worn in the ear - are of particular interest due to their ability…
Rapid Extraction of Respiratory Waveforms from Photoplethysmography: A Deep Encoder Approach
Harry J. Davies, Danilo P. Mandic
Much of the information of breathing is contained within the photoplethysmography (PPG) signal, through changes in venous blood flow, heart rate and stroke volume. We aim to levera…
An Apparatus for the Simulation of Breathing Disorders: Physically Meaningful Generation of Surrogate Data
Harry J. Davies, Ghena Hammour, Hongjian Xiao +1
The rapidly increasing prevalence of debilitating breathing disorders, such as chronic obstructive pulmonary disease (COPD), calls for a meaningful integration of artificial intell…
In-Ear SpO2 for Classification of Cognitive Workload
Harry J. Davies, Ian Williams, Ghena Hammour +3
Classification of cognitive workload promises immense benefit in diverse areas ranging from driver safety to augmenting human capability through closed loop brain computer interfac…
In-Ear Measurement of Blood Oxygen Saturation: An Ambulatory Tool Needed To Detect The Delayed Life-Threatening Hypoxaemia in COVID-19
Harry J. Davies, Ian Williams, Nicholas S. Peters +1
Non-invasive ambulatory estimation of blood oxygen saturation has emerged as an important clinical requirement to detect hypoxemia in the delayed post-infective phase of COVID-19,…