Scholarlink

<p>Across the primate cortex, neurons with similar functions tend to cluster spatially, a principle that extends across many species and reflects a common strategy for organizing sensory processing. In the visual cortex, this appears as modular clusters tuned to specific visual features. Although short connections are widely believed to support such organization, the underlying neural mechanisms remain unclear. Here, we show that artificial deep neural networks develop topographic maps resembling those in primary, intermediate, and high-level human visual cortex when their units include local lateral connections and are trained through standard top-down credit assignment. Notably, this modular organization emerges without any explicitly imposed topography-inducing objectives or learning rules, suggesting that local lateral connections alone can drive the formation of cortical-like maps. Incorporating such lateral connections also improves model robustness to subtle, adversarial perturbations, highlighting an additional computational role for local recurrent structure in shaping robust visual representations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Local lateral connectivity is sufficient for replicating cortex-like topographical organization in deep neural networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月17日

查看全文
  • Xinyu Qian,
  • Amir Ozhan Dehghani,
  • Asa Borzabadi Farahani,
  • Pouya Bashivan

摘要

Across the primate cortex, neurons with similar functions tend to cluster spatially, a principle that extends across many species and reflects a common strategy for organizing sensory processing. In the visual cortex, this appears as modular clusters tuned to specific visual features. Although short connections are widely believed to support such organization, the underlying neural mechanisms remain unclear. Here, we show that artificial deep neural networks develop topographic maps resembling those in primary, intermediate, and high-level human visual cortex when their units include local lateral connections and are trained through standard top-down credit assignment. Notably, this modular organization emerges without any explicitly imposed topography-inducing objectives or learning rules, suggesting that local lateral connections alone can drive the formation of cortical-like maps. Incorporating such lateral connections also improves model robustness to subtle, adversarial perturbations, highlighting an additional computational role for local recurrent structure in shaping robust visual representations.