Liu Zhaofan, Du CongCong, Wong-Lin KongFatt, Wang Da-Hui
Peking University HuiLongGuan Clinical Medical School, Beijing Huilongguan Hospital, Beijing, China.
School of Systems Science, Beijing Normal University, Beijing, China.
Front Neural Circuits. 2025 Aug 18;19:1574877. doi: 10.3389/fncir.2025.1574877. eCollection 2025.
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 architecture. 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 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.
蝴蝶结架构（BTA）在生物神经系统中广泛存在，但其自发形成的潜在机制仍不清楚。在本研究中，我们通过在多种分类任务中受生物启发的非负连接约束下训练多层神经网络，确定了一种新的形成机制。我们表明，非负权重通过放大反向传播的误差信号和抑制隐藏层活动来重塑网络动态，从而导致无需预定义架构的BTA自组织。据我们所知，这是首次证明仅非负性就能诱导BTA形成。由此产生的架构具有明显的功能优势，包括更低的布线成本、对缩放的鲁棒性和任务通用性，突出了其计算效率和生物学相关性。我们的发现为BTA的出现提供了一种机制解释，并将生物结构与人工学习原理联系起来。
