Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A complex-valued RTRL algorithm for recurrent neural networks.

Su Lee Goh1, Danilo P Mandic

  • 1Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, UK. su.goh@imperial.ac.uk

Neural Computation
|November 2, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

A novel backpropagation algorithm based on negated kurtosis loss for training shallow, convolutional, and deep neural networks.

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

How to Evaluate Signal Quality of ear-ECG?

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Impact of Pulmonary Vein Isolation on Atrial Fibrillation Organisation: Correlation of Intracardiac and Surface Electrocardiogram Measures.

Journal of cardiovascular electrophysiology·2025
Same author

UAdam: Unified Adam-Type Algorithmic Framework for Nonconvex Optimization.

Neural computation·2024
Same author

From Scalp to Ear-EEG: A Generalizable Transfer Learning Model for Automatic Sleep Scoring in Older People.

IEEE journal of translational engineering in health and medicine·2024
Same author

Physically Meaningful Surrogate Data for COPD.

IEEE open journal of engineering in medicine and biology·2024
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

A new complex-valued real-time recurrent learning (CRTRL) algorithm enhances nonlinear adaptive filters using recurrent neural networks. This method effectively processes complex signals, outperforming existing real-valued approaches.

Area of Science:

  • * Computational neuroscience
  • * Signal processing
  • * Machine learning

Background:

  • * Nonlinear adaptive filters are crucial for processing complex signals.
  • * Existing methods often struggle with complex-valued, nonstationary, or correlated data.
  • * Recurrent neural networks offer a powerful framework for adaptive filtering.

Purpose of the Study:

  • * To introduce a novel complex-valued real-time recurrent learning (CRTRL) algorithm.
  • * To extend the capabilities of nonlinear adaptive filters to complex-valued signals.
  • * To provide a generic algorithm applicable to various complex signal processing tasks.

Main Methods:

  • * Development of a CRTRL algorithm for fully connected recurrent neural networks.
  • * Derivation of the algorithm for a general complex activation function.

Related Experiment Videos

  • * Simulation and evaluation using benchmark and real-world complex-valued signals.

    • Main Results:

    • * The CRTRL algorithm demonstrates suitability for nonlinear adaptive filtering of complex signals.
    • * The approach effectively handles nonlinear, nonstationary, and correlated complex-valued signals.
    • * Simulations confirm the algorithm's performance and validity.

    Conclusions:

    • * The proposed CRTRL algorithm is a significant advancement in complex-valued adaptive filtering.
    • * It offers a versatile and effective solution for processing complex and challenging signal types.
    • * The algorithm represents a natural and powerful extension of real-valued adaptive learning methods.