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

A Hierarchical Predictive Coding Model of Object Recognition in Natural Images.

M W Spratling1

  • 1Department of Informatics, King's College London, Strand, London, WC2R 2LS UK.

Cognitive Computation
|April 18, 2017
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

Shape-Texture Debiased Training for Robust Template Matching.

Sensors (Basel, Switzerland)·2022
Same journal

Keying Into Cognition: Temporal Smoothing of Smartphone Typing Behaviors for Passive Assessment of Processing Speed and Executive Function in Individuals With Mood Disorders.

Cognitive computation·2026
Same journal

Neurodynamical Computing at the Information Boundaries of Intelligent Systems.

Cognitive computation·2024
Same journal

Large-Kernel Attention for 3D Medical Image Segmentation.

Cognitive computation·2024
Same journal

Spiking Recurrent Neural Networks Represent Task-Relevant Neural Sequences in Rule-Dependent Computation.

Cognitive computation·2023
Same journal

Robust Resting-State Dynamics in a Large-Scale Spiking Neural Network Model of Area CA3 in the Mouse Hippocampus.

Cognitive computation·2023
Same journal

Deep Learning Based Traffic Prediction Method for Digital Twin Network.

Cognitive computation·2023
See all related articles

This study demonstrates predictive coding, a model of brain processing, can accurately recognize objects in natural images. The PC/BC-DIM algorithm shows practical visual object recognition capabilities, a first for predictive coding models.

Area of Science:

  • Computational neuroscience
  • Artificial intelligence
  • Computer vision

Background:

  • Predictive coding models hierarchical perceptual inference in the cortex.
  • Previous studies lacked demonstrations of predictive coding for complex object recognition in natural images.

Purpose of the Study:

  • To propose and evaluate a hierarchical neural network based on predictive coding for visual object recognition.
  • To demonstrate the practical capabilities of predictive coding in complex image recognition tasks.

Main Methods:

  • Development of a hierarchical neural network implementing predictive coding (PC/BC-DIM algorithm).
  • Application of the network to diverse visual recognition tasks: handwritten digit categorization, face identification, and car localization in street scenes.
Keywords:
Deep neural networksImplicit shape modelNeural networksObject recognitionPredictive codingSparse coding

Related Experiment Videos

Main Results:

  • The proposed network successfully performed visual object recognition tasks.
  • The system exhibited tolerance to variations in position, illumination, size, partial occlusion, and within-category differences.
  • Achieved accurate visual object recognition, demonstrating practical application of predictive coding.

Conclusions:

  • This work provides the first practical demonstration of predictive coding's efficacy in visual object recognition.
  • The PC/BC-DIM algorithm implementation shows significant potential for real-world image recognition applications.
  • The findings support predictive coding as a viable computational model for complex perceptual inference in artificial systems.