Task-Driven Convolutional Recurrent Models of the Visual System
Task-Driven Convolutional Recurrent Models of the Visual System
复制标题
DOI：
--
复制
发表时间：
2018-06
影响因子：
5.7
通讯作者：
Aran Nayebi;Daniel Bear;J. Kubilius;Kohitij Kar;S. Ganguli;David Sussillo;J. DiCarlo;Daniel Yamins
中科院分区：
文献类型：
--
作者：
Aran Nayebi;Daniel Bear;J. Kubilius;Kohitij Kar;S. Ganguli;David Sussillo;J. DiCarlo;Daniel Yamins
前馈卷积神经网络（CNN）目前是ImageNet等对象分类任务的最新技术。此外，它们是灵长类动物大脑视觉系统中神经元时间平均反应的定量准确模型。然而，生物视觉系统有两个普遍存在的结构特征，这两个特征与典型的CNN不同：皮质区域内的局部复发，以及从下游区域到上游区域的远程反馈。在这里，我们探讨了递归在提高分类性能中的作用。我们发现，标准形式的递归（vanilla RNN和LSTM）在ImageNet任务的深度CNN中表现不佳。相比之下，包含两个结构特征（旁路和门控）的新型细胞能够大幅提高任务准确性。我们将这些设计原则扩展到数千个模型架构的自动搜索中，这些架构识别出了对对象识别有用的新的局部递归细胞和远程反馈连接。此外，这些任务优化的ConvRNN比前馈网络更好地匹配灵长类视觉系统中的神经活动动态，这表明大脑的周期性连接在执行困难的视觉行为中发挥了作用。
Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain's visual system. However, biological visual systems have two ubiquitous architectural features not shared with typical CNNs: local recurrence within cortical areas, and long-range feedback from downstream areas to upstream areas. Here we explored the role of recurrence in improving classification performance. We found that standard forms of recurrence (vanilla RNNs and LSTMs) do not perform well within deep CNNs on the ImageNet task. In contrast, novel cells that incorporated two structural features, bypassing and gating, were able to boost task accuracy substantially. We extended these design principles in an automated search over thousands of model architectures, which identified novel local recurrent cells and long-range feedback connections useful for object recognition. Moreover, these task-optimized ConvRNNs matched the dynamics of neural activity in the primate visual system better than feedforward networks, suggesting a role for the brain's recurrent connections in performing difficult visual behaviors.