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

Combining reconstruction and discrimination with class-specific sparse coding.

Stephan Hasler1, Heiko Wersing, Edgar Körner

  • 1Honda Research Institute Europe GmbH, Offenbach/Main, Germany. Stephan.hasler@honda-ri.de

Neural Computation
|May 25, 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

Train your robot in AR: insights and challenges for humans and robots in continual teaching and learning.

Frontiers in robotics and AI·2025
Same author

Toward Self-Referential Autonomous Learning of Object and Situation Models.

Cognitive computation·2016
Same author

[Archives of 200 years of Swiss veterinary medicine].

Schweizer Archiv fur Tierheilkunde·2016
Same author

Evidence for Emergency Vaccination Having Played a Crucial Role to Control the 1965/66 Foot-and-Mouth Disease Outbreak in Switzerland.

Frontiers in veterinary science·2015
Same author

[Between empiricism and evidence - ( re ) activation of veterinary phytotherapy].

Forschende Komplementarmedizin (2006)·2014
Same author

Structural synaptic plasticity has high memory capacity and can explain graded amnesia, catastrophic forgetting, and the spacing effect.

PloS one·2014
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

This study introduces two novel supervised sparse coding methods to enhance sensory feature learning for classification. These methods balance representational power with improved classification suitability.

Area of Science:

  • Machine Learning
  • Computer Vision
  • Signal Processing

Background:

  • Sparse coding is a key unsupervised learning technique for extracting sensory features.
  • Traditional sparse coding lacks direct optimization for downstream tasks like classification.
  • Enhancing feature representations for classification is crucial in machine learning.

Purpose of the Study:

  • To develop and evaluate novel sparse coding methods incorporating supervised information.
  • To improve the classification performance of learned features while preserving general representation capabilities.
  • To analyze the impact of supervised components on feature representation quality.

Main Methods:

  • Extension of traditional sparse coding with supervised components.

Related Experiment Videos

  • Utilizing data visualization techniques to analyze feature representation.
  • Testing the methods on artificial datasets and two real-world object recognition datasets.

    • Main Results:

    • The proposed methods demonstrate increased suitability of learned features for classification tasks.
    • Analysis shows a balance between classification-specific and general feature representation.
    • Visualization provides insights into the properties of the learned feature representations.

    Conclusions:

    • Supervised sparse coding effectively enhances features for classification.
    • The developed methods offer a promising approach for representation learning in supervised contexts.
    • Further analysis confirmed the utility of the learned features across different datasets.