Daniel Dimanov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Daniel Dimanov has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Colin Singleton
University of Reading
2 shared publications - Shahin Rostami
Data Science Lab, Polyra Limited, Bournemouth, UK
2 shared publications Emili Balaguer-Ballester
1 shared publication- Emili Balaguer-Ballester
Department of Computing and Informatics, Bournemouth University, Poole, United Kingdom
1 shared publication
Latest Publications
- 19 May 2024
- Published by Springer Nature
- p. 526-538
RAMOSS - Resource Aware Multi-Objective Semantic Segmentation Through Neuroevolution
- 19 May 2024
- Published by Springer Nature
- p. 526-538
RAMOSS - Resource Aware Multi-Objective Semantic Segmentation Through Neuroevolution
- Open Access
MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders
In this paper, we present a novel neuroevolutionary method to identify the architecture and hyperparameters of convolutional autoencoders. Remarkably, we used a hypervolume indicator in the context of neural architecture search for autoencoders, for the first time to our current knowledge. Results show that images were compressed by a factor of more than 10, while still retaining enough information to achieve image classification for the majority of the tasks. Thus, this new approach can be used to speed up the AutoML pipeline for image compression.
Open AccessMONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders
In this paper, we present a novel neuroevolutionary method to identify the architecture and hyperparameters of convolutional autoencoders. Remarkably, we used a hypervolume indicator in the context of neural architecture search for autoencoders, for the first time to our current knowledge. Results show that images were compressed by a factor of more than 10, while still retaining enough information to achieve image classification for the majority of the tasks. Thus, this new approach can be used to speed up the AutoML pipeline for image compression.