Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Downsampling

Downsampling

When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...

Upsampling

Upsampling

Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Impact of antibiotic prophylaxis courses on postoperative complications following total joint arthroplasty: Finding from Chinese population.

Journal of clinical pharmacy and therapeutics·2021

Same author

Time-course alterations of gut microbiota and short-chain fatty acids after short-term lincomycin exposure in young swine.

Applied microbiology and biotechnology·2021

Same author

Collaborative Assessment and Health Risk of Heavy Metals in Soils and Tea Leaves in the Southwest Region of China.

International journal of environmental research and public health·2021

Same author

Trends of Antibiotic Use and Expenditure After an Intensified Antimicrobial Stewardship Policy at a 2,200-Bed Teaching Hospital in China.

Frontiers in public health·2021

Same author

PDZ Binding Kinase/T-LAK Cell-Derived Protein Kinase Plays an Oncogenic Role and Promotes Immune Escape in Human Tumors.

Journal of oncology·2021

Same author

Construction of a Polarity-Switchable Photoelectrochemical Biosensor for Ultrasensitive Detection of miRNA-141.

Analytical chemistry·2021

Same journal

A boundary-regularization-enhanced video anomaly detection network based on context-adaptive spatio-temporal conditional diffusion.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

MT<sup>2</sup>-CSD and LLM-CRAN: A new dataset and an LLM-based multi-semantic knowledge fusion model for conversational stance detection.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

TriAlignNet: A triple-path cross-modality alignment framework for multimodal time series forecasting.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 8, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Noise-resistant sharpness-aware minimization in deep learning.

Dan Su¹, Long Jin², Jun Wang³

¹School of Information Science and Engineering, Lanzhou University, Lanzhou, China; School of Automation, Central South University, Changsha, China.

Neural Networks : the Official Journal of the International Neural Network Society

|November 2, 2024

Summary

This summary is machine-generated.

This study introduces a novel noise-resistant Sharpness-Aware Minimization (SAM) method to improve model generalization and privacy. The new approach enhances robustness against noise, unlike traditional methods that degrade performance.

Keywords:

Deep neural networks Noise resistance Sharpness-aware minimization

More Related Videos

Fine-tuning the Size and Minimizing the Noise of Solid-state Nanopores

Fine-tuning the Size and Minimizing the Noise of Solid-state Nanopores

Published on: October 31, 2013

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Jun 8, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Fine-tuning the Size and Minimizing the Noise of Solid-state Nanopores

Fine-tuning the Size and Minimizing the Noise of Solid-state Nanopores

Published on: October 31, 2013

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Machine Learning
Artificial Intelligence
Computer Science

Background:

Sharpness-Aware Minimization (SAM) enhances model generalization by reducing loss landscape sharpness.
Current privacy methods often involve adding noise, which can harm model generalization and robustness.
A need exists for methods that balance privacy protection with model performance.

Purpose of the Study:

To develop a noise-resistant Sharpness-Aware Minimization (SAM) method.
To enhance model generalization and privacy protection simultaneously.
To analyze the convergence and noise resistance of the proposed method.

Main Methods:

Proposed a novel noise-resistant parameter update rule for SAM.
Analyzed the convergence properties of the method under noisy conditions.
Evaluated the noise resistance of the method.

Main Results:

The proposed noise-resistant SAM method demonstrates improved generalization.
The method offers enhanced privacy protection.
Experimental results confirm the advantages across various datasets and networks.

Conclusions:

The developed noise-resistant SAM method effectively improves model generalization and privacy.
This approach offers a robust solution for training models in noisy environments.
The findings suggest a promising direction for privacy-preserving machine learning.