深度神经网络中的相似性：相似而不同，不同而相似
Paradox in Deep Neural Networks: Similar yet Different while Different yet Similar
摘要：
机器学习正朝着数据科学的方向发展，这意味着有必要进行一系列研究，以揭示深层神经网络所学到的知识。根据地面实况，将网络之间的比较仅限于预定义的智能能力是不够的，它应该与这些人工实体的先天相似性相关联。在这里，我们分析了训练用于对静态图像（CIFAR和ImageNet数据集）中的对象进行分类的相同架构的多个实例。我们评估了网络在各种失真下的性能，并将其与其组成内核之间的内在相似性进行了比较。虽然我们预计这两种措施之间的密切联系，我们观察到一个令人困惑的现象。内核权重相关性超过99.9%的网络对可以表现出显着不同的性能，而其他没有相关性的网络对可以达到相当兼容的性能水平。我们展示了这对迁移学习的影响，并论证了它在我们对智能是什么的一般理解中的重要性，无论是自然的还是人工的。
英文摘要：
Machine learning is advancing towards a data-science approach, implying a necessity to a line of investigation to divulge the knowledge learnt by deep neuronal networks. Limiting the comparison among networks merely to a predefined intelligent ability, according to ground truth, does not suffice, it should be associated with innate similarity of these artificial entities. Here, we analysed multiple instances of an identical architecture trained to classify objects in static images (CIFAR and ImageNet data sets). We evaluated the performance of the networks under various distortions and compared it to the intrinsic similarity between their constituent kernels. While we expected a close correspondence between these two measures, we observed a puzzling phenomenon. Pairs of networks whose kernels' weights are over 99.9% correlated can exhibit significantly different performances, yet other pairs with no correlation can reach quite compatible levels of performance. We show implications of this for transfer learning, and argue its importance in our general understanding of what intelligence is, whether natural or artificial.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
