The current state-of-the-art object recognition algorithms, deep convolutional neural networks (DCNNs), are inspired by the architecture of the mammalian visual system, and are capable of human-level performance on many tasks. As they are trained for object recognition tasks, it has been shown that DCNNs develop hidden representations that resemble those observed in the mammalian visual system (Razavi and Kriegeskorte, 2014; Yamins and Dicarlo, 2016; Gu and van Gerven, 2015; Mcclure and Kriegeskorte, 2016). Moreover, DCNNs trained on object recognition tasks are currently among the best models we have of the mammalian visual system. This led us to hypothesize that teaching DCNNs to achieve even more brain-like representations could improve their performance. To test this, we trained DCNNs on a composite task, wherein networks were trained to: (a) classify images of objects; while (b) having intermediate representations that resemble those observed in neural recordings from monkey visual cortex. Compared with DCNNs trained purely for object categorization, DCNNs trained on the composite task had better object recognition performance and are more robust to label corruption. Interestingly, we found that neural data was not required for this process, but randomized data with the same statistical properties as neural data also boosted performance. While the performance gains we observed when training on the composite task vs the “pure” object recognition task were modest, they were remarkably robust. Notably, we observed these performance gains across all network variations we studied, including: smaller (CORNet-Z) vs larger (VGG-16) architectures; variations in optimizers (Adam vs gradient descent); variations in activation function (ReLU vs ELU); and variations in network initialization. Our results demonstrate the potential utility of a new approach to training object recognition networks, using strategies in which the brain – or at least the statistical properties of its activation patterns – serves as a teacher signal for training DCNNs.

当前最先进的对象识别算法，即深度卷积神经网络（DCNN），受到哺乳动物视觉系统架构的启发，能够在许多任务上达到人类水平。在训练对象识别任务的过程中，已显示DCNN会发展出类似于哺乳动物视觉系统中观察到的隐藏表示（Razavi和Kriegeskorte，2014； Yamins和Dicarlo，2016； Gu和van Gerven，2015； Mcclure和Kriegeskorte ，2016）。而且，经过对象识别任务训练的DCNN目前是我们拥有的哺乳动物视觉系统的最佳模型之一。这使我们假设，教DCNN以获得更多类似于大脑的表示方式可以改善其性能。为了测试这一点，我们对DCNN进行了复合任务训练，其中网络被训练为：（a）分类物体的图像；（b）具有类似于猴子视皮层神经记录中观察到的中间表示。与仅针对对象分类训练的DCNNs相比，经过复合任务训练的DCNNs具有更好的对象识别性能，并且在标记损坏方面更强大。有趣的是，我们发现此过程不需要神经数据，但是具有与神经数据相同的统计属性的随机数据也可以提高性能。尽管我们在进行复合任务与“纯”对象识别任务的训练时观察到的性能提升是适度的，但它们却非常强大。值得注意的是，我们在研究的所有网络版本中都观察到了这些性能提升，其中包括：较小（CORNet-Z）与较大（VGG-16）架构；优化器的变化（Adam与梯度下降）；激活功能的变化（ReLU与ELU）；网络初始化的变化。我们的研究结果证明了一种新的方法用于训练对象识别网络的潜在效用，该策略使用大脑（至少是其激活模式的统计特性）作为训练DCNN的教师信号的策略。