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

Vector quantization of neural networks.

W C Chu1, N K Bose

  • 1Department of Electrical Engineering, The Spatial and Temporal Signal Processing Center, The Pennsylvania State University, University Park, PA 16802, USA.

IEEE Transactions on Neural Networks
|February 8, 2008
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

Exosomes derived from human embryonic mesenchymal stem cells promote osteochondral regeneration.

Osteoarthritis and cartilage·2016
Same author

Absorption of penicillin from the nose and alimentary canal.

Proceedings of the Society for Experimental Biology and Medicine. Society for Experimental Biology and Medicine (New York, N.Y.)·2010
Same author

Miscellaneous pharmacologic actions of citrinin.

The Journal of laboratory and clinical medicine·2010
Same author

Allergic sensitization to penicillin; experimental results.

Proceedings of the Society for Experimental Biology and Medicine. Society for Experimental Biology and Medicine (New York, N.Y.)·2010
Same author

Effects of some old and proposed anticonvulsants on the threshold for electrical convulsions.

Proceedings of the Society for Experimental Biology and Medicine. Society for Experimental Biology and Medicine (New York, N.Y.)·2010
Same author

High resolution image formation from low resolution frames using Delaunay triangulation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·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

This study explores vector quantization for neural network parameters, comparing optimal and suboptimal methods. Multistage quantizers provide the best balance of performance and complexity for speech signal prediction.

Area of Science:

  • Machine Learning
  • Signal Processing
  • Data Compression

Background:

  • Neural network parameter optimization is crucial for efficient deployment.
  • Vector quantization offers a method for compressing these parameters.
  • Evaluating different quantization strategies is necessary for practical applications.

Purpose of the Study:

  • To address the problem of vector quantizing neural network parameters.
  • To compare the performance of various quantization algorithms.
  • To identify optimal and suboptimal quantization schemes.

Main Methods:

  • Described optimal and suboptimal quantization schemes.
  • Conducted simulations using nonlinear prediction of speech signals.
  • Evaluated performance based on complexity and accuracy tradeoffs.

Related Experiment Videos

Main Results:

  • Compared multiple quantization techniques for speech signal prediction.
  • Identified performance and implementational complexity tradeoffs.
  • Demonstrated that multistage quantizers offer the best balance.

Conclusions:

  • Multistage quantizers present a superior tradeoff between complexity and performance.
  • The findings are relevant for efficient neural network design and deployment.
  • Vector quantization is a viable technique for neural network parameter compression.