Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Insights from the Use of Previously Unseen Neural Architecture Search Datasets
Rob Geada, David Towers, Matthew Forshaw +2
The boundless possibility of neural networks which can be used to solve a problem -- each with different performance -- leads to a situation where a Deep Learning expert is require…
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…