ORIGINAL RESEARCH article
Front. Neural Circuits
Volume 19 - 2025 | doi: 10.3389/fncir.2025.1574877
This article is part of the Research TopicNeuro-inspired computationView all 8 articles
Non-Negative Connectivity Causes Bow-Tie Architecture in Neural Circuits
Provisionally accepted
- 1Department of Systems Science and National Key Laboratory of Cognitive Science and Learning, Beijing Normal University, Beijing, China
- 2Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems, Ulster University, Magee Campus, Derry∼Londonderry, United Kingdom
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Bow-tie architecture (BTA) is widely observed in biological neural systems, yet the underlying mechanism driving its spontaneous emergence remains unclear. In this study, we identify a novel formation mechanism by training multi-layer neural networks under biologically inspired non-negative connectivity constraints across diverse classification tasks. We show that non-negative weights reshape network dynamics by amplifying back-propagated error signals and suppressing hidden-layer activity, leading to the self-organization of BTA without pre-defined architectural. To our knowledge, this is the first demonstration that non-negativity alone can induce BTA formation. The resulting architecture confers distinct functional advantages, including lower 1 wiring cost, robustness to scaling, and task generalizability, highlighting both its computational efficiency and biological relevance. Our findings offer a mechanistic account of BTA emergence and bridge biological structure with artificial learning principles.
Keywords: Bow-tie architecture, neural circuits, Non-negative connectivity, computational neuroscience, robustness, Efficiency, discrimination tasks, backpropagation algorithm
Received: 11 Feb 2025; Accepted: 21 Jul 2025.
Copyright: © 2025 Liu, DU, Wong-Lin and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
KongFatt Wong-Lin, Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems, Ulster University, Magee Campus, Derry∼Londonderry, United Kingdom
Da-Hui Wang, Department of Systems Science and National Key Laboratory of Cognitive Science and Learning, Beijing Normal University, Beijing, 100875, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.