None Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology

AI学习规则与早期灵长类视觉一致，在较高区域出现分歧

作者 PulseAugur 编辑部 · [2 sources] · 2026-05-21 12:31

研究人员发表了一项研究，比较了人工神经网络中的不同学习规则与人类和猕猴视觉处理过程的匹配程度。研究发现，早期视觉皮层的对齐在物种间是保守的，人工神经网络与猕猴电生理学数据的相关性高于与人类fMRI数据的相关性。然而，在IT皮层等较高视觉区域，学习规则的对齐排名在物种间存在显著差异，这表明模型容量和训练数据在这些区域比具体的学习规则起着更大的作用。 AI

影响这项研究为人工神经网络如何更好地模拟生物视觉系统提供了见解，可能指导未来AI开发，以实现更高效、更像人类的视觉处理。

排序理由该集群包含一篇详细阐述新研究发现的学术论文。

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.LG TIER_1 · Nils Leutenegger · 2026-05-22 04:00

Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology

arXiv:2605.22401v1 Announce Type: new Abstract: Does the relationship between learning rules and brain alignment generalize across species? We extend our prior finding that untrained CNNs match backpropagation at human V1 by testing the same five learning rules against macaque el…
arXiv cs.NE (Neural & Evolutionary) TIER_1 · Nils Leutenegger · 2026-05-21 12:31

Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology

Does the relationship between learning rules and brain alignment generalize across species? We extend our prior finding that untrained CNNs match backpropagation at human V1 by testing the same five learning rules against macaque electrophysiology. The rules are backpropagation (…

报道来源 [2]

Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology

Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology

相关实体

相关话题