Using goal-driven deep learning models to understand sensory cortex
Using goal-driven deep learning models to understand sensory cortex
复制标题
DOI：
10.1038/nn.4244
复制
发表时间：
2016-03-01
影响因子：
25
通讯作者：
DiCarlo, James J.
中科院分区：
文献类型：
--
作者：
Yamins, Daniel L. K.;DiCarlo, James J.
在计算机视觉和人工智能社区创新的推动下，计算神经科学的最新发展已经使用目标驱动的分层卷积神经网络（HCNN）在建模高级视觉皮层区域的神经单元和群体反应方面取得了长足的进步。在本视角中，我们回顾了更广泛的建模背景下的最新进展，并描述了支持它的一些关键技术创新。然后，我们概述了如何使用目标驱动的 HCNN 方法来更深入地了解感觉皮层处理的发展和组织。
Fueled by innovation in the computer vision and artificial intelligence communities, recent developments in computational neuroscience have used goal-driven hierarchical convolutional neural networks (HCNNs) to make strides in modeling neural single-unit and population responses in higher visual cortical areas. In this Perspective, we review the recent progress in a broader modeling context and describe some of the key technical innovations that have supported it. We then outline how the goal- driven HCNN approach can be used to delve even more deeply into understanding the development and organization of sensory cortical processing.