用果蝇幼虫脑连接组构建神经网络，性能超传统模型。
Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures
- 将果蝇脑连接图转为固定循环网络BPU，直接基于真实突触连接。
- 未修改的BPU在MNIST上达98%准确率，CIFAR-10达58%，优于同规模MLP。
- 轻量级GNN-BPU仅用1万局棋谱即达60%走法准确率，远超同类Transformer。
果蝇幼虫大脑的完整连接组为检验生物演化电路是否能支撑人工智能提供了独特机会。我们将这一布线图转化为生物保真处理单元（BPU），一种直接源自突触连接的固定递归网络。尽管规模较小（3,000个神经元，65,000个权重），未经修改的BPU在MNIST上达到98%准确率，在CIFAR-10上达58%，超过同规模多层感知机（MLP）。通过结构化连接组扩展进行缩放，进一步提升CIFAR-10表现；模态特异性消融实验揭示了不同感官子系统贡献不均。在ChessBench数据集上，仅用10,000局训练的轻量级GNN-BPU模型达到60%走法准确率，接近同类Transformer的10倍。此外，约200万参数的CNN-BPU模型在参数匹配下优于同等规模Transformer，结合深度6的极小值搜索推理时，准确率达91.7%，超过900万参数的Transformer基线。这些结果表明，生物保真神经架构具备支持复杂认知任务的潜力，为未来更大更智能连接组的拓展提供动力。
原文摘要 · Abstract (English)
The complete connectome of the Drosophila larva brain offers a unique opportunity to investigate whether biologically evolved circuits can support artificial intelligence. We convert this wiring diagram into a Biological Processing Unit (BPU), a fixed recurrent network derived directly from synaptic connectivity. Despite its modest size 3,000 neurons and 65,000 weights between them), the unmodified BPU achieves 98% accuracy on MNIST and 58% on CIFAR-10, surpassing size-matched MLPs. Scaling the BPU via structured connectome expansions further improves CIFAR-10 performance, while modality-specific ablations reveal the uneven contributions of different sensory subsystems. On the ChessBench dataset, a lightweight GNN-BPU model trained on only 10,000 games achieves 60% move accuracy, nearly 10x better than any size transformer. Moreover, CNN-BPU models with ~2M parameters outperform parameter-matched Transformers, and with a depth-6 minimax search at inference, reach 91.7% accuracy, exceeding even a 9M-parameter Transformer baseline. These results demonstrate the potential of biofidelic neural architectures to support complex cognitive tasks and motivate scaling to larger and more intelligent connectomes in future work.
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。