Mitigating Noise

Mitigating noise in various machine learning contexts is a crucial research area aiming to improve model accuracy and robustness. Current efforts focus on developing noise-mitigation techniques tailored to specific architectures, such as incorporating denoising blocks in deep neural networks or employing pre-training strategies in differentially private federated learning, and leveraging spectral robustness in graph-based models. These advancements are significant because they enhance the reliability and efficiency of machine learning models across diverse applications, from image classification and wind turbine control to long-term sequence forecasting. The ultimate goal is to create more resilient and accurate systems capable of handling real-world data with inherent imperfections.

Papers

November 7, 2024

Impact of white noise in artificial neural networks trained for classification: performance and noise mitigation strategies
Nadezhda Semenova, Daniel Brunner
Neural Network Classification Code System Performance Softmax Function Neural Computation Analog Neural Network Background Noise Mitigating Noise

September 27, 2024

Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators
Seyedarmin Azizi, Mohammad Erfan Sadeghi, Mehdi Kamal, Massoud Pedram
Deep Neural Network Native Robustness Denoising Process DNN Framework Inference Efficiency Analog Neural Network Mixed Signal Mitigating Noise

August 18, 2024

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training
Huitong Jin, Yipeng Zhou, Laizhong Cui, Quan Z. Sheng
Pre Trained Model Private Federated Learning Pre Training Model Model Gradient Mitigating Noise

July 18, 2024

Deep Reinforcement Learning for Multi-Objective Optimization: Enhancing Wind Turbine Energy Generation while Mitigating Noise Emissions
Martín de Frutos, Oscar A. Marino, David Huergo, Esteban Ferrer
Deep Reinforcement Learning Multi Objective Optimization Wind Turbine Mitigating Noise

January 28, 2024

Addressing Noise and Efficiency Issues in Graph-Based Machine Learning Models From the Perspective of Adversarial Attack
Yongyu Wang
Adversarial Attack High Efficiency Visual Perspective Graph Based Learning Graph Construction Graph Algorithm Mitigating Noise

December 28, 2023

Learning the Dynamic Correlations and Mitigating Noise by Hierarchical Convolution for Long-term Sequence Forecasting
Zhihao Yu, Liantao Ma, Yasha Wang, Junfeng Zhao
Convolutional Neural Network Transformer Based Model Direct Convolution Deep Learning Algorithm Hierarchical Memory Mitigating Noise Dynamic Correlation

April 20, 2022

Noise mitigation strategies in physical feedforward neural networks
Nadezhda Semenova, Daniel Brunner
Neural Network Single Neuron Correlated Noise Transformer Feed Forward Layer Noise Tolerant Network Mitigating Noise

Mitigating Noise

Papers

Impact of white noise in artificial neural networks trained for classification: performance and noise mitigation strategies

Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training

Deep Reinforcement Learning for Multi-Objective Optimization: Enhancing Wind Turbine Energy Generation while Mitigating Noise Emissions

Addressing Noise and Efficiency Issues in Graph-Based Machine Learning Models From the Perspective of Adversarial Attack

Learning the Dynamic Correlations and Mitigating Noise by Hierarchical Convolution for Long-term Sequence Forecasting

Noise mitigation strategies in physical feedforward neural networks