Correntropy Learning

Correntropy learning is a robust statistical learning framework designed to improve the accuracy and reliability of machine learning models in the presence of noisy data, particularly non-Gaussian noise. Current research focuses on integrating correntropy with various model architectures, including recurrent neural networks, Bayesian learning methods, and logistic regression, often incorporating techniques like automatic relevance determination for feature selection and improved sparsity. This approach enhances the performance of applications ranging from brain-computer interfaces and signal processing (e.g., inertial measurement unit orientation estimation) to pedestrian trajectory prediction, demonstrating its value across diverse fields dealing with real-world, imperfect data.

Papers

April 1, 2024

Sparse Bayesian Correntropy Learning for Robust Muscle Activity Reconstruction from Noisy Brain Recordings
Yuanhao Li, Badong Chen, Natsue Yoshimura, Yasuharu Koike, Okito Yamashita
Neural Recording Sparse Bayesian Learning Sparse Bayesian Correntropy Learning

February 22, 2024

Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion
Pauline Bourigault, Dongpo Xu, Danilo P. Mandic
Neural Network Quaternion Valued Convolutional Neural Network Real Time Recurrent Learning Maximum Correntropy Criterion Quaternion Property Correntropy Learning

November 26, 2023

IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction
Yuehai Chen
Long Short Term Memory Trajectory Prediction Pedestrian Trajectory Prediction Human Interaction Interaction Representation Human Human Interaction Correntropy Learning

April 13, 2023

Multi-kernel Correntropy-based Orientation Estimation of IMUs: Gradient Descent Methods
Shilei Li, Lijing Li, Dawei Shi, Yunjiang Lou, Ling Shi
Gradient Descent Inertial Measurement Unit Maximum Likelihood Orientation Estimation Correntropy Learning

July 20, 2022

Correntropy-Based Logistic Regression with Automatic Relevance Determination for Robust Sparse Brain Activity Decoding
Yuanhao Li, Badong Chen, Yuxi Shi, Natsue Yoshimura, Yasuharu Koike
High Dimensional Relevance Modeling Correntropy Learning

October 20, 2021

CIM-PPO:Proximal Policy Optimization with Liu-Correntropy Induced Metric
Yunxiao Guo, Han Long, Xiaojun Duan, Kaiyuan Feng, Maochu Li, Xiaying Ma
Reinforcement Learning Policy Gradient Proximal Policy Optimization KL Divergence PPO Algorithm Correntropy Learning

Correntropy Learning

Papers

Sparse Bayesian Correntropy Learning for Robust Muscle Activity Reconstruction from Noisy Brain Recordings

Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion

IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction

Multi-kernel Correntropy-based Orientation Estimation of IMUs: Gradient Descent Methods

Correntropy-Based Logistic Regression with Automatic Relevance Determination for Robust Sparse Brain Activity Decoding

CIM-PPO:Proximal Policy Optimization with Liu-Correntropy Induced Metric