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

arXiv: https://arxiv.org/abs/2407.05650 · HTML: https://mlsanity.com/paper/2407.05650/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 72 references that are in the map.
- First posted on arXiv 8 Jul 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks](https://mlsanity.com/paper/2107.01729/) (2021)
- [Properties of Sparse Distributed Representations and their Application to Hierarchical Temporal Memory](https://mlsanity.com/paper/1503.07469/) (2015)
- [A Theory of Natural Intelligence](https://mlsanity.com/paper/2205.00002/) (2022)
- [Trace and Detect Adversarial Attacks on CNNs using Feature Response Maps](https://mlsanity.com/paper/2208.11436/) (2022)
- [Fodor and Pylyshyn's Critique of Connectionism and the Brain as Basis of the Mind](https://mlsanity.com/paper/2307.14736/) (2023)

## Abstract (arXiv)

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 figure completion 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.