• Home
  • Search
  • The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns.
  • Cite Icon1
  • https://doi.org/10.1162/neco.a.1505Copy DOI Icon

The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns.

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

We introduce the cooperative network architecture (CNA), a model that represents sensory signals using structured, recurrently connected networks of neurons, termed "nets." Nets are dynamically assembled from overlapping net fragments, which are learned based on statistical regularities in sensory input. This architecture offers robustness to noise, deformation, and generalization to out-of-distribution data, addressing challenges in current vision systems from a novel perspective. We demonstrate that net fragments can be learned without supervision and flexibly recombined to encode novel patterns, enabling figurecompletion and resilience to noise. Our findings establish CNA as a promising paradigm for developing neural representations that integrate local feature processing with global structure formation, providing a foundation for future research on invariant object recognition.

Similar Papers
  • PDF
  • Research Article
  • Citations28

A chicken model for studying the emergence of invariant object recognition

  • Feb 26, 2015
  • Frontiers in Neural Circuits
  • Samantha M W Wood +1
  • PDF
  • Research Article
  • Citations8

Invariant recognition of visual objects: some emerging computational principles.

  • Jan 01, 2012
  • Frontiers in computational neuroscience
  • Evgeniy Bart +1
  • PDF
  • Research Article
  • Citations2

Invariant object recognition based on extended fragments

  • Aug 24, 2012
  • Frontiers in Computational Neuroscience
  • Evgeniy Bart +1
  • Peer Review Report

Decision letter: Neural markers of predictive coding under perceptual uncertainty revealed with Hierarchical Frequency Tagging

  • Dec 20, 2016
  • Klaas Enno Stephan
  • Research Article
  • Citations3

Exploiting Cooperation for Performance Enhancement and High Data Rates

  • Apr 01, 2009
  • Journal of Communications
  • Tatiana K Madsen +3
  • Research Article
  • Citations128

Storage of a sensory pattern by anti-Hebbian synaptic plasticity in an electric fish.

  • May 15, 1993
  • Proceedings of the National Academy of Sciences
  • C C Bell +3
  • Conference Article
  • Citations12

Invariant object recognition by shape space analysis

  • Oct 04, 1998
  • J Zhang +2
  • Research Article

A Multifactor Winner-Take-All Dynamics

  • Apr 14, 2011
  • Neural Computation
  • Junmei Zhu
  • Research Article
  • Citations95

2-D invariant object recognition using distributed associative memory

  • Jan 01, 1988
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • H Wechsler +1
  • Research Article
  • Citations9

Measuring the speed of newborn object recognition in controlled visual worlds.

  • Nov 04, 2016
  • Developmental Science
  • Justin N Wood +1
  • Book Chapter

Models of invariant object recognition

  • Nov 01, 2001
  • Edmund T. Rolls
  • Book Chapter

Invariant Object Recognition Using Circular Pairwise Convolutional Networks

  • Jul 21, 2006
  • Choon Hui Teo +1
  • Book Chapter

Invariant object recognition using fahlman and Lebiere's learning algorithm

  • Jan 01, 1993
  • Kazuki Ito +3
  • PDF
  • Research Article
  • Citations55

Feeding state, insulin and NPR-1 modulate chemoreceptor gene expression via integration of sensory and circuit inputs.

  • Oct 30, 2014
  • PLoS Genetics
  • Matthew Gruner +8
  • Research Article
  • Citations41

Neural Prediction Errors Distinguish Perception and Misperception of Speech.

  • Jun 11, 2018
  • The Journal of Neuroscience
  • Helen Blank +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.