Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence.
Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence.
复制标题
DOI：
10.1038/srep27755
复制
发表时间：
2016-06-10
影响因子：
4.6
通讯作者：
Oliva A
中科院分区：
文献类型：
--
作者：
Cichy RM;Khosla A;Pantazis D;Torralba A;Oliva A
皮层视觉通路复杂的多级架构为人类有效的视觉对象识别提供了神经基础。然而，其中的分阶段计算仍然知之甚少。在这里，我们将时间（脑磁图）和空间（功能 MRI）视觉大脑表征与根据现实世界视觉识别统计数据调整的人工深度神经网络（DNN）中的表征进行了比较。我们表明，DNN 捕获了人类视觉处理在时间和空间上的各个阶段，从早期视觉区域到背侧和腹侧流。对关键 DNN 参数的进一步研究表明，虽然模型架构很重要，但为了加强与大脑的时空层次关系，需要对现实世界进行分类训练。我们的结果共同为人类视觉大脑中视觉对象识别的时空动态提供了基于算法的视图。
The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain.