Brunel University Research Archive(BURA) preserves and enables easy and open access to all
types of digital content. It showcases Brunel's research outputs.
Research contained within BURA is open access, although some publications may be subject
to publisher imposed embargoes. All awarded PhD theses are also archived on BURA.
Browsing by Author Byerly, A
Showing results 1 to 8 of 8
| Issue Date | Title | Author(s) |
|---|---|---|
| 2020 | A Branching and Merging Convolutional Network with Homogeneous Filter Capsules | Kalganova, T; Byerly, A; Dear, I |
| 8-Feb-2022 | Class Density and Dataset Quality in High-Dimensional, Unstructured Data | Byerly, A; Kalganova, T |
| 7-Jul-2022 | The Current State of the Art in Deep Learning for Image Classification: A Review | Byerly, A; Kalganova, T; Ott, R |
| 17-Mar-2021 | Homogeneous Vector Capsules Enable Adaptive Gradient Descent in Convolutional Neural Networks | Byerly, A; Kalganova, T |
| 20-Sep-2019 | Homogeneous Vector Capsules Enable Adaptive Gradient Descent in Convolutional Neural Networks | Byerly, A; Kalganova, T |
| 19-Aug-2021 | no Routing Needed Between Capsules | Kalganova, T; Byerly, A; Dear, I |
| 8-Jul-2021 | On the Importance of Capturing a Sufficient Diversity of Perspective for the Classification of micro-PCBs | Byerly, A; Kalganova, T; Grichnik, AJ |
| 7-Jan-2023 | Towards an Analytical Definition of Sufficient Data | Byerly, A; Kalganova, T |