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

Circular backpropagation networks embed vector quantization.

S Ridella, S Rovetta, R Zunino

IEEE Transactions on Neural Networks

|February 7, 2008

Summary

This summary is machine-generated.

This study demonstrates the equivalence between vector quantization (VQ) classifiers and circular backpropagation (CBP) networks. VQ prototypes can initialize CBP networks, improving optimization for classification tasks like handwritten digit recognition.

Related Experiment Videos

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

Imaging artifacts in MRI simulators.

The neuroradiology journal·2013

Same author

Study of bound water of poly-adenine using high frequency dielectric measurements.

Biophysical journal·2009

Same author

Representation and generalization properties of class-entropy networks.

IEEE transactions on neural networks·2008

Same author

Worst case analysis of weight inaccuracy effects in multilayer perceptrons.

IEEE transactions on neural networks·2008

Same author

Empirical measure of multiclass generalization performance: the K-winner machine case.

IEEE transactions on neural networks·2008

Same author

K-winner machines for pattern classification.

IEEE transactions on neural networks·2008

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

Area of Science:

Machine Learning
Artificial Intelligence
Pattern Recognition

Background:

Vector Quantization (VQ) is a data compression technique.
Circular Backpropagation (CBP) networks are a type of neural network.
Both VQ and CBP are used in classification tasks.

Discussion:

This letter establishes a formal equivalence between VQ classifiers and CBP networks.
It shows that VQ prototypes can be directly used in CBP feedforward structures.
This equivalence allows for effective initialization of CBP networks using VQ prototypes.

Key Insights:

VQ classifiers and CBP networks are mathematically equivalent.
VQ prototypes provide a meaningful initialization strategy for CBP optimization.
This approach was validated on the NIST handwritten digits dataset.

Outlook:

Potential for improved performance in classification tasks.
Further exploration of VQ-CBP network applications.
Development of new hybrid models combining VQ and CBP strengths.