English(EN) Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks

受生物学启发的神经网络利用小鼠大脑数据

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-12 21:53

研究人员通过利用MICrONS项目的数据，开发了受生物学启发的循环神经网络。该项目结合了小鼠视觉皮层电子显微镜和钙成像数据。这些网络利用了近12,000个神经元的神经元空间坐标、解剖连接和功能衍生关系来初始化权重，并在学习过程中施加空间约束。研究发现，结合了皮层结构和功能的网络在三个认知决策任务上的表现明显优于基线模型，其中功能权重初始化带来的收益最为显著。 AI

影响受生物学启发的网络架构可能带来更高效、更有效的学习算法。

排序理由该集群包含一篇详细介绍神经网络新研究的学术论文。

在 arXiv cs.NE (Neural & Evolutionary) 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Mo Shakiba, Rana Rokni, Mohammad Mohammadi, Nima Dehghani · 2026-06-16 04:00

Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks

arXiv:2606.14975v1 Announce Type: cross Abstract: How the wiring and functional organization of cortex shape recurrent computation remains a central question in both neuroscience and machine learning. Here, we leverage data released through the Machine Intelligence from Cortical …
arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Nima Dehghani · 2026-06-12 21:53

Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks

How the wiring and functional organization of cortex shape recurrent computation remains a central question in both neuroscience and machine learning. Here, we leverage data released through the Machine Intelligence from Cortical Networks (MICrONS) program--a functional connectom…

报道来源 [2]

Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks

Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks

相关实体

相关话题