Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, MA, USA.
Department of Computer Science, The University of Western Ontario, London, ON, Canada.
Sci Rep. 2020 Mar 13;10(1):4638. doi: 10.1038/s41598-020-61409-0.
Research at the intersection of computer vision and neuroscience has revealed hierarchical correspondence between layers of deep convolutional neural networks (DCNNs) and cascade of regions along human ventral visual cortex. Recently, studies have uncovered emergence of human interpretable concepts within DCNNs layers trained to identify visual objects and scenes. Here, we asked whether an artificial neural network (with convolutional structure) trained for visual categorization would demonstrate spatial correspondences with human brain regions showing central/peripheral biases. Using representational similarity analysis, we compared activations of convolutional layers of a DCNN trained for object and scene categorization with neural representations in human brain visual regions. Results reveal a brain-like topographical organization in the layers of the DCNN, such that activations of layer-units with central-bias were associated with brain regions with foveal tendencies (e.g. fusiform gyrus), and activations of layer-units with selectivity for image backgrounds were associated with cortical regions showing peripheral preference (e.g. parahippocampal cortex). The emergence of a categorical topographical correspondence between DCNNs and brain regions suggests these models are a good approximation of the perceptual representation generated by biological neural networks.
计算机视觉和神经科学的交叉研究揭示了深度卷积神经网络（DCNN）的层与人类腹侧视觉皮层区域的级联之间的层次对应关系。最近的研究发现，在经过训练以识别视觉对象和场景的 DCNN 层中，出现了人类可解释的概念。在这里，我们想知道，经过视觉分类训练的人工神经网络（具有卷积结构）是否会表现出与大脑区域表现出中央/外围偏向的空间对应关系。使用表示相似性分析，我们将用于对象和场景分类的 DCNN 的卷积层的激活与人类大脑视觉区域中的神经表示进行了比较。结果表明，DCNN 的层中存在类似于大脑的拓扑组织，即具有中央偏向的层单元的激活与具有中央倾向的大脑区域（例如梭状回）相关，而对图像背景具有选择性的层单元的激活与表现出外围偏好的皮层区域（例如海马旁回）相关。DCNN 与大脑区域之间出现的分类拓扑对应关系表明，这些模型是生物神经网络产生的感知表示的良好近似。
