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

Parametric embedding for class visualization.

Tomoharu Iwata1, Kazumi Saito, Naonori Ueda

  • 1NTT Communication Science Laboratories, Kyoto, Japan. iwata@cslab.kecl.ntt.co.jp

Neural Computation
|July 26, 2007
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

Nonlinear combinatorial analysis of blood transcriptomes identifies PRKAR1A as a regulator of TDP-43 pathophysiology in amyotrophic lateral sclerosis.

Biology methods & protocols·2026
Same author

A folk taxonomy of magic.

Cognition·2026
Same author

A reporting checklist for large language models in behavioural science.

Nature human behaviour·2026
Same author

Resolving Feynman's restaurant problem reveals optimal solutions and human strategies.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Considering Psychological Mechanisms Can Change the Interpretation of Bayesian Models.

Topics in cognitive science·2026
Same author

Conniving With Continuations: Representing Goals in a Domain-Specific Language of Thought.

Topics in cognitive science·2026
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

We introduce Parametric Embedding (PE), a novel method for visualizing data structures. PE efficiently embeds objects into low-dimensional spaces, offering insights into classifier behavior across various learning settings.

Area of Science:

  • Machine Learning
  • Data Visualization
  • Computational Statistics

Background:

  • Visualizing high-dimensional data is crucial for understanding complex datasets.
  • Existing embedding methods can be computationally intensive, especially for large datasets.
  • Understanding classifier behavior in different learning paradigms (supervised, semi-supervised, unsupervised) is essential.

Purpose of the Study:

  • To propose a new embedding method, Parametric Embedding (PE), for visualizing data with inherent class structures.
  • To develop a computationally efficient method for dimensionality reduction and data visualization.
  • To provide insights into classifier performance across supervised, semi-supervised, and unsupervised learning tasks.

Main Methods:

  • Parametric Embedding (PE) embeds objects with class structure into a low-dimensional space.

Related Experiment Videos

  • The method utilizes class conditional probabilities as input.
  • It minimizes the sum of Kullback-Leibler divergences, assuming a Gaussian mixture model with equal covariances in the embedding space.

    • Main Results:

    • PE demonstrates computational advantages over methods relying on pairwise object relations.
    • The algorithm's complexity scales with the product of the number of objects and classes.
    • Successful visualization of supervised web page categorization, semi-supervised digit categorization, and unsupervised topic modeling (Latent Dirichlet Allocation) relations.

    Conclusions:

    • Parametric Embedding (PE) is an effective and efficient method for visualizing structured data.
    • PE offers valuable insights into classifier behavior in diverse machine learning settings.
    • The method has broad applicability, from supervised classification to unsupervised topic discovery.