Spectral Adaptive Dropout: Frequency-Based Regularization for Improved Generalization
Deep neural networks are often susceptible to overfitting, necessitating effective regularization techniques. This paper introduces Spectral Adaptive Dropout, a novel frequency-based regularization technique that dynamically adjusts dropout rates based on the spectral characteristics of network grad...
Saved in:
Main Authors: | Zhigao Huang, Musheng Chen, Shiyan Zheng |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2025-06-01
|
Series: | Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2078-2489/16/6/475 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Enhancing Efficiency and Regularization in Convolutional Neural Networks: Strategies for Optimized Dropout
by: Mehdi Ghayoumi
Published: (2025-05-01) -
Spectral Mapping Using Kernel Principal Components Regression for Voice Conversion
by: Peng SONG, et al.
Published: (2013-03-01) -
Anomaly Detection Approach Based on Deep Neural Network and Dropout
by: Zaid Hussien et al.
Published: (2020-06-01) -
Student Dropout at a Newly Established University
by: Emmanuel L. Howe, et al.
Published: (2025-06-01) -
Refitting Previous Presbyopic Contact Lens Dropouts with a Single Use Multifocal Contact Lens
by: Fogt JS, et al.
Published: (2025-07-01)