Shared spatiotemporal category representations in biological and artificial deep neural networks.
Shared spatiotemporal category representations in biological and artificial deep neural networks.
复制标题
DOI：
10.1371/journal.pcbi.1006327
复制
发表时间：
2018-07
影响因子：
4.3
通讯作者：
Hansen BC
中科院分区：
文献类型：
--
作者：
Greene MR;Hansen BC
视觉场景类别表示的出现非常迅速，但实现这种不变分类的计算转换仍然难以捉摸。深度卷积神经网络（cnn）使用前馈架构以接近人类水平的精度执行视觉分类，为神经科学家提供了评估一系列成功的表征转换的机会，这些转换使计算机分类成为可能。当前研究的目标是通过高密度的时间分辨事件相关电位（ERPs）评估，评估由CNN构建的序列场景类别表征与人脑构建的序列场景类别表征之间的程度。我们发现了时间和头皮之间的对应关系：更早（0-200 ms）的ERP活动最好的解释是所有电极上的早期CNN层。虽然大多数电极位置的后期活动与早期的CNN层相对应，但右侧枕颞电极的活动最好解释为刺激后225 ms左右的较晚的、完全连接的CNN层，以及额叶电极的类似模式。综上所述，这些结果表明场景类别表征的出现是通过枕叶电极的早期活动以及颞叶和额叶电极的后期活动之间的动态相互作用而发展起来的。我们可以快速而轻松地对视觉场景进行分类，但对实现这一壮举的神经处理阶段仍然知之甚少。在并行发展中，深度卷积神经网络（cnn）已经被开发出来，可以以类似人类的精度进行视觉分类。我们假设CNN的处理阶段可能与人脑的处理阶段相似。我们发现事实确实如此，早期的大脑信号最好由CNN的早期阶段解释，而后期的大脑信号由后来的CNN层解释。我们还发现，特定类别的信息似乎首先出现在感觉皮层，然后迅速传递到额叶区域。生物大脑和人工神经网络之间的相似性为神经科学家提供了通过研究人工系统来更好地理解分类过程的机会。
Visual scene category representations emerge very rapidly, yet the computational transformations that enable such invariant categorizations remain elusive. Deep convolutional neural networks (CNNs) perform visual categorization at near human-level accuracy using a feedforward architecture, providing neuroscientists with the opportunity to assess one successful series of representational transformations that enable categorization in silico. The goal of the current study is to assess the extent to which sequential scene category representations built by a CNN map onto those built in the human brain as assessed by high-density, time-resolved event-related potentials (ERPs). We found correspondence both over time and across the scalp: earlier (0–200 ms) ERP activity was best explained by early CNN layers at all electrodes. Although later activity at most electrode sites corresponded to earlier CNN layers, activity in right occipito-temporal electrodes was best explained by the later, fully-connected layers of the CNN around 225 ms post-stimulus, along with similar patterns in frontal electrodes. Taken together, these results suggest that the emergence of scene category representations develop through a dynamic interplay between early activity over occipital electrodes as well as later activity over temporal and frontal electrodes. We categorize visual scenes rapidly and effortlessly, but still have little insight into the neural processing stages that enable this feat. In a parallel development, deep convolutional neural networks (CNNs) have been developed that perform visual categorization with human-like accuracy. We hypothesized that the stages of processing in a CNN may parallel the stages of processing in the human brain. We found that this is indeed the case, with early brain signals best explained by early stages of the CNN and later brain signals explained by later CNN layers. We also found that category-specific information seems to first emerge in sensory cortex and is then rapidly fed up to frontal areas. The similarities between biological brains and artificial neural networks provide neuroscientists with the opportunity to better understand the process of categorization by studying the artificial systems.
登录
查看更多内容
影响因子：
8.2
作者：
Greene MR;Oliva A
通讯作者：
Oliva A
影响因子：
5.7
作者：
Goddard, Erin;Carlson, Thomas A.;Woolgar, Alexandra
通讯作者：
Woolgar, Alexandra
影响因子：
5.3
作者：
Guclu, Umut;van Gerven, Marcel A. J.
通讯作者：
van Gerven, Marcel A. J.
影响因子：
4.6
作者：
Cichy RM;Khosla A;Pantazis D;Torralba A;Oliva A
通讯作者：
Oliva A
影响因子：
1.8
作者：
Chauvin, A;Worsley, KJ;Gosselin, F
通讯作者：
Gosselin, F