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

Bilinear sparse coding for invariant vision.

David B Grimes1, Rajesh P N Rao

  • 1Department of Computer Science and Engineering, University of Washington, Seattle, WA 98195-2350, USA. grimes@cs.washington.edu

Neural Computation
|November 27, 2004
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 authorSame journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same author

Culturally-attuned AI: Implicit learning of altruistic cultural values through inverse reinforcement learning.

PloS one·2025
Same author

Predictive coding with spiking neural networks: A survey.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Average of Baseline Autocorrelation Function is a Leading Indicator of Neural Stimulation Data Quality.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Learning Temporal Basis Vectors for Closed-Loop Neural Stimulation.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

A survey on neuro-mimetic deep learning via predictive coding.

Neural networks : the official journal of the International Neural Network Society·2025
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

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 a new unsupervised algorithm for learning image features and their transformations. The sparse bilinear model enables transformation-invariant vision by learning features and their movements simultaneously.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Image Processing

Background:

  • Sparse coding and Independent Component Analysis (ICA) algorithms learn localized features from natural images.
  • Existing methods do not account for image transformations, limiting their applicability.
  • Learning the same feature across multiple locations is a significant limitation of prior work.

Purpose of the Study:

  • To develop an unsupervised algorithm for learning both localized features and their transformations from images.
  • To address the limitations of previous sparse coding and ICA approaches.
  • To achieve transformation-invariant vision by modeling feature interactions.

Main Methods:

  • Utilized a sparse bilinear generative model for unsupervised learning.

Related Experiment Videos

  • Trained the algorithm on an arbitrary set of natural images.
  • Focused on learning oriented basis filters that represent features and their transformations.

    • Main Results:

    • The algorithm successfully produces oriented basis filters capable of representing image features and their transformations.
    • The learned generative model allows for the translation of features to different locations.
    • Demonstrated a reduction in the need to learn identical features at multiple positions.

    Conclusions:

    • Explicitly modeling the interaction between local image features and their transformations is key.
    • The sparse bilinear approach offers a foundation for achieving transformation-invariant vision.
    • This method overcomes limitations of previous sparse coding and ICA techniques by handling feature transformations.