As convolutional neural networks (CNNs) become more accurate at object recognition, their representations become more similar to the primate visual system. This finding has inspired us and other researchers to ask if the implication also runs the other way: If CNN representations become more brain-like, does the network become more accurate? Previous attempts to address this question showed very modest gains in accuracy, owing in part to limitations of the regularization method. To overcome these limitations, we developed a new neural data regularizer for CNNs that uses Deep Canonical Correlation Analysis (DCCA) to optimize the resemblance of the CNN's image representations to that of the monkey visual cortex. Using this new neural data regularizer, we see much larger performance gains in both classification accuracy and within-super-class accuracy, as compared to the previous state-of-the-art neural data regularizers. These networks are also more robust to adversarial attacks than their unregularized counterparts. Together, these results confirm that neural data regularization can push CNN performance higher, and introduces a new method that obtains a larger performance boost.
翻译:随着进化神经网络(CNNs)在目标识别方面变得更加准确,它们的表达方式与灵长类视觉系统更加相似。这一发现激励我们和其他研究人员询问其含义是否也具有相反效果:如果CNN的表达方式更像大脑,网络是否更准确?以前处理这一问题的尝试显示,由于正规化方法的局限性,准确性提高幅度很小。为了克服这些限制,我们为CNN开发了一个新的神经数据常规化系统,使用深显性相近分析(DCCA)来优化CNN的图像表达方式与猴子视觉皮层图像的相似性。使用这个新的神经数据常规化系统,我们看到了在分类精度和超级级精确性两方面的性能提高幅度,而与以前的状态神经数据规范者相比,这些网络对对抗性攻击的力度也比非常规化的对应者还要强。加起来,这些结果证实神经数据规范化可以提高CNN的性能,并引入了一种获得更大性能增强的新方法。