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

Deterministic learning and rapid dynamical pattern recognition.

Cong Wang¹, David J Hill

¹College of Automation and the Center for Control and Optimization, South China University of Technology, Guangzhou 510641, PR China. wangcong@scut.edu.cn

IEEE Transactions on Neural Networks

|May 29, 2007

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

Repeated exposure to sevoflurane impairs the learning and memory of older male rats.

Life sciences·2017

Same author

Stationary state distribution and efficiency analysis of the Langevin equation via real or virtual dynamics.

The Journal of chemical physics·2017

Same author

Optimized production and isolation of antibacterial agent from marine <i>Aspergillus flavipes</i> against <i>Vibrio harveyi</i>.

3 Biotech·2017

Same author

Preparation and antioxidant properties of low molecular holothurian glycosaminoglycans by H<sub>2</sub>O<sub>2</sub>/ascorbic acid degradation.

International journal of biological macromolecules·2017

Same author

Associations between single-nucleotide polymorphisms in the NTRK1 gene and basal pain sensitivity in young Han Chinese women.

Neuroscience letters·2017

Same author

Design, synthesis and antiproliferative effect of 17β-amide derivatives of 2-methoxyestradiol and their studies on pharmacokinetics.

Steroids·2017

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

This study introduces a deterministic framework for rapid recognition of dynamical patterns. The approach transforms pattern recognition into analyzing the stability of a recognition error system, enabling efficient temporal pattern identification.

Area of Science:

Artificial Intelligence
Machine Learning
Dynamical Systems

Background:

Recognizing temporal or dynamical patterns presents significant challenges in pattern recognition.
Existing methods may struggle with the complexities of time-varying data.
Deterministic learning theory offers potential for novel pattern recognition approaches.

Purpose of the Study:

To propose a deterministic framework for the rapid recognition of dynamical patterns.
To represent time-varying dynamical patterns in a time-invariant, spatially distributed manner.
To establish a novel similarity measure for dynamical patterns based on inherent system dynamics.

Main Methods:

Utilizing deterministic learning theory to represent dynamical patterns.

Related Experiment Videos

Defining a similarity metric based on system dynamics and state synchronization.

Developing a recognition mechanism involving internal, dynamical matching of system dynamics.

Analyzing the stability and convergence of a recognition error system.

Main Results:

Demonstrated effective representation of time-varying patterns in a time-invariant manner.
Introduced a similarity measure based on achieving state synchronization through dynamical matching.
Showcased that recognition error can quantify pattern similarity.
Simulation studies confirmed the approach's effectiveness.

Conclusions:

The proposed deterministic framework offers a novel and effective method for dynamical pattern recognition.
The approach successfully converts dynamical pattern recognition into a problem of system stability and convergence.
This dynamical approach provides a computationally efficient solution for complex temporal pattern identification.