在廣度、深度與時間上擴展神經網路

摘要

空間與時間的資源限制對生物與人工智慧系統皆至關重要。在此，我們針對一個被視為無限點陣中有限子集的遞迴卷積神經網路，定義了關於廣度、深度與時間的可微分代價項。透過反向傳播，我們將這些代價與任務誤差共同最佳化。透過對廣度、深度與時間施加不同程度的壓力，多樣化的計算圖在訓練過程中自然湧現。我們發現，這三種資源可以相互權衡，以達到特定準確度水準。隨著任務複雜度增加，網路在三個維度上同步成長，且當輸入被遮蔽時，網路會自發性地採取更多遞迴步驟。令人驚訝的是，模型所耗費的時間與人類在物體辨識任務中的反應時間具有相關性。本框架提供了一個規範性說明，闡述資源限制如何塑造神經架構，並連結到神經科學中關於腦部設計的疑問，同時可能有助於闡明自然界中神經解方之多樣性。

English

Spatial and temporal resource constraints are critical for both biological and artificial intelligent systems. Here we define differentiable cost terms for breadth, depth, and time within a recurrent convolutional neural network conceived as a finite subset of an infinite lattice. We optimize these costs jointly with task errors via backpropagation. We set different pressures on breadth, depth, and time, which leads to diverse computational graphs emerging organically through training. We find that all three resources can be traded off against each other to achieve a given level of accuracy. Networks grow in all three dimensions with task complexity and spontaneously take more recurrent steps when inputs are occluded. Surprisingly, time used by the model correlates with human reaction times in an object recognition task. Our framework provides a normative account of how resource constraints shape neural architectures, connecting to questions about brain design in neuroscience, and may help illuminate the diversity of neural solutions found in nature.