Enhancing Efficiency and Regularization in Convolutional Neural Networks: Strategies for Optimized Dropout

Enhancing Efficiency and Regularization in Convolutional Neural Networks: Strategies for Optimized Dropout

<b>Background/Objectives:</b> Convolutional Neural Networks (CNNs), while effective in tasks such as image classification and language processing, often experience overfitting and inefficient training due to static, structure-agnostic regularization techniques like traditional dropout. T...

Full description

Saved in:
Bibliographic Details
Main Author: Mehdi Ghayoumi
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:AI
Subjects:
convolutional neural networks (CNNs)
probabilistic feature importance dropout (PFID)
regularization techniques
adaptive learning
network efficiency
Online Access:https://www.mdpi.com/2673-2688/6/6/111
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/2673-2688/6/6/111

Similar Items