تقرير
MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders
| العنوان: | MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders |
|---|---|
| المؤلفون: | Dimanov, Daniel, Balaguer-Ballester, Emili, Singleton, Colin, Rostami, Shahin |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Neural and Evolutionary Computing, Computer Science - Machine Learning |
| الوصف: | 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. Comment: Published as a Poster paper in ICLR 2021 Neural Architecture Search workshop |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2106.11914 |
| رقم الأكسشن: | edsarx.2106.11914 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |