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

Discriminant pattern recognition using transformation-invariant neurons.

D Sona1, A Sperduti, A Starita

  • 1Dipartimento di Informatica, Università di Pisa, Italy.

Neural Computation
|August 10, 2000
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

Multi-task learning for the prediction of wind power ramp events with deep neural networks.

Neural networks : the official journal of the International Neural Network Society·2020
Same author

The neutron camera upgrade for MAST Upgrade.

The Review of scientific instruments·2018
Same author

Compositional generative mapping for tree-structured data--part II: topographic projection model.

IEEE transactions on neural networks and learning systems·2014
Same author

A general framework for adaptive processing of data structures.

IEEE transactions on neural networks·2008
Same author

On the implementation of frontier-to-root tree automata in recursive neural networks.

IEEE transactions on neural networks·2008
Same author

A self-organizing map for adaptive processing of structured data.

IEEE transactions on neural networks·2008
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

TD-Neuron, a novel gradient-descent algorithm, enhances invariant pattern recognition by developing discriminant models. It outperforms singular value decomposition (SVD) and learning vector quantization (LVQ) algorithms in error-rejection trade-offs.

Area of Science:

  • Computer Science
  • Machine Learning
  • Pattern Recognition

Background:

  • Invariant pattern recognition is a challenge in machine learning.
  • Nearest-neighbor approaches using tangent distance achieve high accuracy but require significant computational resources.
  • Singular Value Decomposition (SVD)-based algorithms like HSS were developed to reduce computational load.

Purpose of the Study:

  • To introduce a new gradient-descent constructive algorithm, TD-Neuron, for developing discriminant models in pattern recognition.
  • To compare the performance of TD-Neuron against existing HSS and Learning Vector Quantization (LVQ) algorithms.
  • To evaluate the effectiveness of TD-Neuron in achieving a better trade-off between error and rejection rates.

Main Methods:

  • Development of the TD-Neuron algorithm, a gradient-descent constructive approach.

Related Experiment Videos

  • Implementation and testing of the HSS algorithm using both two-sided and one-sided tangent distance.
  • Comparative analysis of TD-Neuron, HSS, and LVQ algorithms on the NIST-3 database.

    • Main Results:

    • TD-Neuron demonstrates superior performance compared to both SVD-based (HSS) and LVQ algorithms.
    • The proposed TD-Neuron algorithm achieves a more favorable balance between classification error and rejection rates.
    • Empirical results on the NIST-3 database validate the effectiveness of TD-Neuron.

    Conclusions:

    • TD-Neuron offers an effective alternative for invariant pattern recognition, outperforming existing methods.
    • The algorithm provides a superior trade-off between error and rejection, crucial for practical applications.
    • This constructive approach advances the development of discriminant models in pattern recognition.