The brain successfully performs visual object recognition with a limited number of hierarchical networks that are much shallower than artificial deep neural networks (DNNs) that perform similar tasks. Here, we show that long-range horizontal connections (LRCs), often observed in the visual cortex of mammalian species, enable such a cost-efficient visual object recognition in shallow neural networks. Using simulations of a model hierarchical network with convergent feedforward connections and LRCs, we found that the addition of LRCs to the shallow feedforward network significantly enhances the performance of networks for image classification, to a degree that is comparable to much deeper networks. We found that a combination of sparse LRCs and dense local connections dramatically increases performance per wiring cost. From network pruning with gradient-based optimization, we also confirmed that LRCs could emerge spontaneously by minimizing the total connection length while maintaining performance. Ablation of emerged LRCs led to a significant reduction of classification performance, which implies these LRCs are crucial for performing image classification. Taken together, our findings suggest a brain-inspired strategy for constructing a cost-efficient network architecture to implement parsimonious object recognition under physical constraints such as shallow hierarchical depth.

大脑使用有限数量的层次网络成功执行视觉对象识别，这些层次网络比执行类似任务的人工深度神经网络（DNN）浅得多。在这里，我们显示了通常在哺乳动物物种的视觉皮层中观察到的远程水平连接（LRC），可以在浅层神经网络中实现这种经济高效的视觉对象识别。通过使用具有收敛前馈连接和LRC的模型分层网络的仿真，我们发现将LRC添加到浅层前馈网络中可以显着提高图像分类网络的性能，其程度可与更深层的网络相比。我们发现，稀疏的LRC和密集的本地连接的组合极大地提高了每条布线成本的性能。通过基于梯度优化的网络修剪，我们还确认了LRC可以通过在保持性能的同时最小化总连接长度来自发出现。出现的LRC的消融导致分类性能显着降低，这意味着这些LRC对于执行图像分类至关重要。综上所述，我们的发现提出了一种启发大脑的策略，该策略可用于构造一种经济高效的网络体系结构，以在诸如浅层次深度的物理约束下实现简约的对象识别。这意味着这些LRC对于执行图像分类至关重要。综上所述，我们的发现提出了一种启发大脑的策略，该策略可用于构造一种经济高效的网络体系结构，以在诸如浅层次深度的物理约束下实现简约的对象识别。这意味着这些LRC对于执行图像分类至关重要。综上所述，我们的发现提出了一种启发大脑的策略，该策略可用于构造一种经济高效的网络体系结构，以在诸如浅层次深度的物理约束下实现简约的对象识别。