Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911927863607296 |
|---|---|
| author | Vinhas, Adriano Correia, João Machado, Penousal |
| author_facet | Vinhas, Adriano Correia, João Machado, Penousal |
| contents | Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on labelled data, which can sometimes be costly and hard to obtain. In order to address the first problem, neuroevolution has been proved to be a plausible option to automate the design of DNNs. As for the second problem, self-supervised learning has been used to leverage unlabelled data to learn representations. Our goal is to study how neuroevolution can help self-supervised learning to bridge the gap to supervised learning in terms of performance. In this work, we propose a framework that is able to evolve deep neural networks using self-supervised learning. Our results on the CIFAR-10 dataset show that it is possible to evolve adequate neural networks while reducing the reliance on labelled data. Moreover, an analysis to the structure of the evolved networks suggests that the amount of labelled data fed to them has less effect on the structure of networks that learned via self-supervised learning, when compared to individuals that relied on supervised learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14525 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning Vinhas, Adriano Correia, João Machado, Penousal Neural and Evolutionary Computing Artificial Intelligence Machine Learning Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on labelled data, which can sometimes be costly and hard to obtain. In order to address the first problem, neuroevolution has been proved to be a plausible option to automate the design of DNNs. As for the second problem, self-supervised learning has been used to leverage unlabelled data to learn representations. Our goal is to study how neuroevolution can help self-supervised learning to bridge the gap to supervised learning in terms of performance. In this work, we propose a framework that is able to evolve deep neural networks using self-supervised learning. Our results on the CIFAR-10 dataset show that it is possible to evolve adequate neural networks while reducing the reliance on labelled data. Moreover, an analysis to the structure of the evolved networks suggests that the amount of labelled data fed to them has less effect on the structure of networks that learned via self-supervised learning, when compared to individuals that relied on supervised learning. |
| title | Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning |
| topic | Neural and Evolutionary Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.14525 |