Paying the Price for Reach: Size-Dependent Emergence of Efficient Wiring in Cognitive Recurrent Neural Networks

Aslan, Bilal and Nitschke, Geoff (2025) Paying the Price for Reach: Size-Dependent Emergence of Efficient Wiring in Cognitive Recurrent Neural Networks, Proceedings of 2025 Conference on Artificial Life (ALIFE 2025), Kyoto, Japan.

[thumbnail of 2025-paying-the-price-for-reach-size-dependent-emergence-of-efficient-wiring-in-cognitive-recurrent-neural-networks.pdf] Text
2025-paying-the-price-for-reach-size-dependent-emergence-of-efficient-wiring-in-cognitive-recurrent-neural-networks.pdf
Download (1MB)

Abstract

Artificial neural networks often neglect the physical wiring costs that are crucial to biological nervous systems. This study investigates how incorporating such a biologically inspired wiring constraint influences the structure and function of Recurrent Neural Networks (RNNs) during learning. We systematically varied network size (N) and the strength (λ) of a communicability-weighted spatial regularization penalty applied to RNNs performing a seasonal foraging task requiring short and long-term memory, and decisionmaking. Our results reveal that while all networks achieved high task accuracy, larger networks (N ≥ 100) exhibited different sensitivity patterns to higher penalties (λ) compared to smaller ones (N=50). Increasing λ induced neural network topologies with similarities to biological brains, including sparsity, shorter connection lengths (while preserving crucial long-range connections), increased modularity, and enhanced small-world characteristics. We identify a size-dependent optimum (sweet spot) for λ ∈ [0.05, 0.10] that yields these efficient, brain-like structural properties without compromising functional performance. These results highlight the importance of physical network constraints in shaping adaptive systems, demonstrate how functional networks can self-organize towards efficient topologies under cost pressures and offer design principles for developing neuromorphic systems.

Item Type: Conference paper
Subjects: Computing methodologies > Artificial intelligence
Date Deposited: 13 Oct 2025 12:26
Last Modified: 13 Oct 2025 12:26
URI: https://pubs.cs.uct.ac.za/id/eprint/1750

Actions (login required)

View Item View Item