activity
20162026
most citedTMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text

3 citations · 4 across the 16 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2023

How much data do I need? A case study on medical data

Ayse Betul Cengiz, A. Stephen McGough

The collection of data to train a Deep Learning network is costly in terms of effort and resources. In many cases, especially in a medical context, it may have detrimental impacts.…

cs.LG2022

Explainable Deep Learning to Profile Mitochondrial Disease Using High Dimensional Protein Expression Data

Atif Khan, Conor Lawless, Amy E Vincent +3

Mitochondrial diseases are currently untreatable due to our limited understanding of their pathology. We study the expression of various mitochondrial proteins in skeletal myofibre…

cs.LG2022

SpiderNet: Hybrid Differentiable-Evolutionary Architecture Search via Train-Free Metrics

Rob Geada, Andrew Stephen McGough

Neural Architecture Search (NAS) algorithms are intended to remove the burden of manual neural network design, and have shown to be capable of designing excellent models for a vari…

cs.LG2020

Not Half Bad: Exploring Half-Precision in Graph Convolutional Neural Networks

John Brennan, Stephen Bonner, Amir Atapour-Abarghouei +3

With the growing significance of graphs as an effective representation of data in numerous applications, efficient graph analysis using modern machine learning is receiving a growi…

cs.LG20193 cited

TMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text

Fady Medhat, Mahnaz Mohammadi, Sardar Jaf +6

Handling large corpuses of documents is of significant importance in many fields, no more so than in the areas of crime investigation and defence, where an organisation may be pres…

cs.LG2018

Predicting the Computational Cost of Deep Learning Models

Daniel Justus, John Brennan, Stephen Bonner +1

Deep learning is rapidly becoming a go-to tool for many artificial intelligence problems due to its ability to outperform other approaches and even humans at many problems. Despite…