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

Search research articles

Related Experiment Videos

Adaptive improved natural gradient algorithm for blind source separation.

Jian-Qiang Liu¹, Da-Zheng Feng, Wei-Wei Zhang

¹National Key Laboratory of Radar Signal Processing, Xidian University, Xi'an 710071, China. jqliu@mail.xidian.edu.cn

Neural Computation

|October 22, 2008

Summary

This summary is machine-generated.

Related Concept Videos

Significance of the Gradient Vector

Significance of the Gradient Vector

A surface defined by a function of two variables can be understood by examining how it changes along specific directions. When one variable is held constant, the surface reduces to a curve that reflects variation in the other variable. For example, fixing one variable and moving parallel to a coordinate axis produces a cross-sectional curve. The slope of this curve at a given point represents how the function changes in that particular direction, providing a measure of local steepness.By...

Blind Procedures

Blind Procedures

Ideally, the people who observe and record the children’s behavior are unaware of who was assigned to the experimental or control group, in order to control for experimenter bias. Experimenter bias refers to the possibility that a researcher’s expectations might skew the results of the study. Remember, conducting an experiment requires a lot of planning, and the people involved in the research project have a vested interest in supporting their hypotheses. If the observers knew which child was...

You might also read

Related Articles

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

Sort by

Same author

Gestational Arsenic Exposure Induces Metabolic Dysfunction-Associated Fatty Liver Disease-like Phenotypes in Middle-Aged Offspring.

Environment & health (Washington, D.C.)·2026

Same author

Divergent Trajectories of the Burden of MASLD Attributable to High Fasting Plasma Glucose in China and Globally: A GBD Study 1990-2021 and Projections to 2046.

Gastroenterology research and practice·2026

Same author

Comprehensive Characterization of 98 Chinese Cases of Genetic Creutzfeldt-Jakob Disease With T188K Mutation.

Annals of clinical and translational neurology·2026

Same author

Disruptions in RNA Splicing: A Key Regulator of Cognitive Impairment in Perioperative Neurocognitive Disorders.

Neuroscience bulletin·2026

Same author

Risk factors and a prediction model for false-negative diagnosis in repeat EUS-FNA/B of pancreatic solid lesions following initially nondiagnostic or inconclusive findings.

Endoscopic ultrasound·2026

Same author

[The Prevalence and Epidemiological Characteristics of Monoclonal Gammopathy of Undetermined Significance in the Healthy Individuals of Daqing Region].

Zhongguo shi yan xue ye xue za zhi·2026

Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026

Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026

Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026

Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026

Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026

Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026

See all related articles

We developed an adaptive natural gradient algorithm for blind source separation. This method enhances convergence speed and stability, particularly in dynamic environments, by adaptively controlling learning parameters.

Area of Science:

Signal Processing
Machine Learning
Independent Component Analysis

Background:

Blind source separation (BSS) aims to recover original signals from mixtures.
Existing natural gradient algorithms face challenges in time-varying environments.

Purpose of the Study:

To propose an adaptive improved natural gradient algorithm for robust blind source separation.
To enhance convergence speed, stability, and tracking ability in dynamic conditions.

Main Methods:

Incorporating a momentum term into the natural gradient learning process.
Developing an estimation function for adaptive control of step-size and momentum parameters.
Utilizing backpropagation algorithm principles for learning acceleration.

Related Experiment Videos

Main Results:

Demonstrated improved convergence speed and stability in simulations.
Showcased effective performance in time-varying environments with changing mixing matrices or signal powers.
Verified the algorithm's capability to separate weak, badly scaled, and numerous sources (up to 10).

Conclusions:

The proposed adaptive algorithm offers superior performance for blind source separation.
It is particularly effective in dynamic and challenging signal environments.
The method shows promise for complex real-world signal recovery applications.