Results 141 to 150 of about 1,489 (178)

Linear Discriminant Analysis with Maximum Correntropy Criterion

2013
Linear Discriminant Analysis (LDA) is a famous supervised feature extraction method for subspace learning in computer vision and pattern recognition. In this paper, a novel method of LDA based on a new Maximum Correntropy Criterion optimization technique is proposed.
Wei Zhou, Sei-ichiro Kamata
openaire   +1 more source

Robust Ellipse Fitting With Laplacian Kernel Based Maximum Correntropy Criterion

IEEE Transactions on Image Processing, 2021
The performance of ellipse fitting may significantly degrade in the presence of outliers, which can be caused by occlusion of the object, mirror reflection or other objects in the process of edge detection. In this paper, we propose an ellipse fitting method that is robust against the outliers, and thus maintaining stable performance when outliers can ...
Chenlong Hu, Gang Wang, K. C. Ho, Junli Liang   +3 more
openaire   +2 more sources

Nyström Kernel Algorithm Under Generalized Maximum Correntropy Criterion

IEEE Signal Processing Letters, 2020
The kernel adaptive filters (KAFs) based on the minimum mean square error (MMSE) criterion in reproducing kernel Hilbert space (RKHS) improve the performance of linear adaptive filters but result in instability issues and large burdens of computation and memory in impulsive noises.
Tao Zhang, Shiyuan Wang
openaire   +1 more source

Maximum Correntropy Criterion Based Robust Kalman Filter

2018
In this paper, a novel filter based on maximum correntropy criterion (MCC) and M-estimate theory is proposed. The MCC based Kalman filter (MKF) is developed by combining the MCC and the M-estimate theories into the framework of the classical Kalman filter (CKF). In this way, the measurement outliers can be suppressed.
Liansheng Wang, XingWei Gao, Lijian Yin
openaire   +1 more source

Nonlinear spline adaptive filtering under maximum correntropy criterion

TENCON 2015 - 2015 IEEE Region 10 Conference, 2015
The nonlinear spline adaptive filtering under least mean square (SAF-LMS) uses the mean square error (MSE) based cost function to identify the Wiener-type nonlinear systems, which is rational under the assumption of Gaussian distributions. However, the mere second-order statistics are often not suitable for nonlinear and/or non-Gaussian systems.
null Siyuan Peng, null Zongze Wu, null Xie Zhang, Badong Chen   +3 more
openaire   +1 more source

A robust maximum correntropy criterion for dictionary learning

2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016
We introduce a method that incorporates robustness to one of the main building blocks of sparse modeling: dictionary learning. Particularly, we exploit correntropy to compute the principal components in cases where outliers might be detrimental without proper care.
Carlos A. Loza, Jose C. Principe
openaire   +1 more source

Generalization analysis of deep CNNs under maximum correntropy criterion

Neural Networks
Convolutional neural networks (CNNs) have gained immense popularity in recent years, finding their utility in diverse fields such as image recognition, natural language processing, and bio-informatics. Despite the remarkable progress made in deep learning theory, most studies on CNNs, especially in regression tasks, tend to heavily rely on the least ...
Yingqiao, Zhang, Zhiying, Fang, Jun, Fan
openaire   +2 more sources

Robust principal curves based on maximum correntropy criterion

2013 International Conference on Machine Learning and Cybernetics, 2013
Principal curves are curves which pass throught the ’middle’ of a data cloud. They are sensitive to variances of data clouds. In this paper, we propose a robust principal curve model Correntropy based Principal Curve (CPC) model, based on maximum correntropy criterion (MCC).
null Chun-Guo Li, Bao-Gang Hu
openaire   +1 more source

A maximum correntropy criterion for robust multidimensional scaling

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015
Multidimensional Scaling (MDS) refers to a class of dimensionality reduction techniques applied to pairwise dissimilarities between objects, so that the interpoint distances in the space of reduced dimensions approximate the initial pairwise dissimilarities as closely as possible.
Fotios Mandanas, Constantine Kotropoulos
openaire   +1 more source

Broad learning system based on maximum multi-kernel correntropy criterion

Neural Networks
The broad learning system (BLS) is an effective machine learning model that exhibits excellent feature extraction ability and fast training speed. However, the traditional BLS is derived from the minimum mean square error (MMSE) criterion, which is highly sensitive to non-Gaussian noise.
Haiquan, Zhao, Xin, Lu
openaire   +2 more sources