Report
Incremental Training of Deep Convolutional Neural Networks
| العنوان: | Incremental Training of Deep Convolutional Neural Networks |
|---|---|
| المؤلفون: | Istrate, Roxana, Malossi, Adelmo Cristiano Innocenza, Bekas, Costas, Nikolopoulos, Dimitrios |
| سنة النشر: | 2018 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Computer Science - Learning, Statistics - Machine Learning |
| الوصف: | We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network, we introduce a look-ahead initialization that outperforms the random initialization. We demonstrate that our incremental approach reaches the reference network baseline accuracy. Additionally, it allows to identify smaller partitions of the original state-of-the-art network, that deliver the same final accuracy, by using only a fraction of the global number of parameters. This allows for a potential speedup of the training time of several factors. We report training results on CIFAR-10 for ResNet and VGGNet. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/1803.10232 |
| رقم الانضمام: | edsarx.1803.10232 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |