Back to Search
Start Over
SIRe-Networks: Convolutional neural networks architectural extension for information preservation via skip/residual connections and interlaced auto-encoders.
- Source :
-
Neural Networks . Sep2022, Vol. 153, p386-398. 13p. - Publication Year :
- 2022
-
Abstract
- Improving existing neural network architectures can involve several design choices such as manipulating the loss functions, employing a diverse learning strategy, exploiting gradient evolution at training time, optimizing the network hyper-parameters, or increasing the architecture depth. The latter approach is a straightforward solution, since it directly enhances the representation capabilities of a network; however, the increased depth generally incurs in the well-known vanishing gradient problem. In this paper, borrowing from different methods addressing this issue, we introduce an interlaced multi-task learning strategy, defined SIRe, to reduce the vanishing gradient in relation to the object classification task. The presented methodology directly improves a convolutional neural network (CNN) by preserving information from the input image through interlaced auto-encoders (AEs), and further refines the base network architecture by means of skip and residual connections. To validate the presented methodology, a simple CNN and various implementations of famous networks are extended via the SIRe strategy and extensively tested on five collections, i.e., MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100, and Caltech-256; where the SIRe-extended architectures achieve significantly increased performances across all models and datasets, thus confirming the presented approach effectiveness. • Designing an interlaced multi-task learning approach to affect the gradient. • Further improving the proposed interlaced approach via skip/residual connections. • Applying the proposed SIRe methodology to other well-known architectures. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 08936080
- Volume :
- 153
- Database :
- Academic Search Index
- Journal :
- Neural Networks
- Publication Type :
- Academic Journal
- Accession number :
- 158208718
- Full Text :
- https://doi.org/10.1016/j.neunet.2022.06.030