Enhancing Deeper Layers with Residual Network on CNN Architecture: A Review

DOI

10.2991/978-94-6463-118-0_46How to use a DOI?

Keywords

Residual Network (Resnet); Classification; Detection; Convolution Neural Network

Abstract

The Convolution Neural Network (CNN) architecture is well-suited to performing both detection and classification tasks on image data. The inclusion of layers in the CNN improves its performance whilst training. Adding a lot, on the other hand, will cause the architecture to lose or explode gradients while learning training data. To address this issue, a mechanism for inserting the residual network between two layer blocks, ReLu activation function, and Batch Normalization must be added. In this paper, we examine various past studies that used residual networks in CNN design to validate model performance improvements. The examination of this study’s findings reveals highly substantial outcomes for the prediction of classification and detection tasks for picture data. We infer from previous research findings that the as have adds a deeper layer to the CNN without losing the gradient. In this paper, we examine various past studies that used residual networks in CNN design to validate model performance improvements. The examination of this study’s findings reveals highly substantial outcomes for the prediction of classification and detection tasks for picture data. We infer from previous research findings that the as have adds a deeper layer to the CNN without losing the gradient.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - A. Supani
AU  - Y. Andriani
AU  - Indarto
AU  - H. Saputra
AU  - A. Bahri Joni
AU  - D. Alfian
AU  - A.Taqwa
AU  - A. Silvia H.
PY  - 2023
DA  - 2023/06/26
TI  - Enhancing Deeper Layers with Residual Network on CNN Architecture: A Review
BT  - Proceedings of the 6th FIRST 2022 International Conference (FIRST-ESCSI-22)
PB  - Atlantis Press
SP  - 449
EP  - 457
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-118-0_46
DO  - 10.2991/978-94-6463-118-0_46
ID  - Supani2023
ER  -