Regularization of deep neural network with batch contrastive loss
Neural networks have become deeper in recent years and this has improved its capacity to handle more complex tasks. However, deep neural network has more parameters and is easier to overfit, especially when training samples are insufficient. In this paper, we present a new regularization technique c...
Saved in:
Main Authors: | Tanveer, Muhammad, Tan, Hung-Khoon, Ng, Hui-Fuang, Leung, Maylor Karhang, Chuah, Joon Huang |
---|---|
Format: | Article |
Published: |
Institute of Electrical and Electronics Engineers
2021
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/28105/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Contrastive-regularized U-Net for video anomaly detection
by: Gan, Kian Yu, et al.
Published: (2023) -
Retinal vessel segmentation using deep learning: A review
by: Chen, Chunhui, et al.
Published: (2021) -
Hydrofluoroether impurities—Chemical detection using a deep learning laser speckle contrast evolving spiking neural network
by: Mohd. Salleh, Ali Syariati, et al.
Published: (2020) -
Prototype regularized manifold regularization technique for semi-supervised online extreme learning machine
by: Muhammad Zaly Shah, Muhammad Zafran, et al.
Published: (2022) -
DeepIPR: Deep neural network ownership verification with passports
by: Fan, Lixin, et al.
Published: (2022)