让AI模型像大脑一样组织神经功能，提升性能与生物合理性。
TopoNets: High Performing Vision and Language Models with Brain-Like Topography
- 提出TopoLoss损失函数，实现高效且不牺牲性能的拓扑结构训练。
- 在视觉与语言模型中均达到当前最高性能，具备局部特征处理等脑特性。
- 适合关注脑启发模型、跨模态架构优化的研究者使用。
大脑中的神经元倾向于按功能相近进行空间分布，而现有AI模型缺乏这种拓扑组织。本文提出一种新型损失函数TopoLoss，可在不显著降低任务性能的前提下，促进模型产生空间上有序的拓扑表征。该方法高度可适配，可无缝集成至主流模型架构中。我们在视觉（ResNet-18、ResNet-50、ViT）和语言模型（GPT-Neo-125M、NanoGPT）上验证了该方法，统称为TopoNets。这些模型是目前性能最高的监督式拓扑模型，表现出局部特征处理、低维性与更高效率等类脑特性，并能预测脑区响应，复现视觉与语言皮层的关键拓扑签名。本工作建立了一个稳健且通用的框架，推动高性能、类脑计算策略的实现。
原文摘要 · Abstract (English)
Neurons in the brain are organized such that nearby cells tend to share similar functions. AI models lack this organization, and past efforts to introduce topography have often led to trade-offs between topography and task performance. In this work, we present TopoLoss, a new loss function that promotes spatially organized topographic representations in AI models without significantly sacrificing task performance. TopoLoss is highly adaptable and can be seamlessly integrated into the training of leading model architectures. We validate our method on both vision (ResNet-18, ResNet-50, ViT) and language models (GPT-Neo-125M, NanoGPT), collectively TopoNets. TopoNets are the highest-performing supervised topographic models to date, exhibiting brain-like properties such as localized feature processing, lower dimensionality, and increased efficiency. TopoNets also predict responses in the brain and replicate the key topographic signatures observed in the brain's visual and language cortices. Together, this work establishes a robust and generalizable framework for integrating topography into leading model architectures, advancing the development of high-performing models that more closely emulate the computational strategies of the human brain.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。