随机加权网络的有趣特性：在几乎没有学习的情况下进行泛化
Intriguing Properties of Randomly Weighted Networks: Generalizing While Learning Next to Nothing
摘要：
训练深度神经网络会产生强大的学习表示，表现出良好的泛化能力。在大多数情况下，训练涉及通过反向传播迭代修改网络内部的所有权重。在极限学习机器中，有人建议将网络的第一层设置为固定的随机值，而不是学习它。在本文中，我们建议将这种方法更进一步，固定深度卷积神经网络的几乎所有层，只允许学习一小部分权重。正如我们的实验所示，即使是固定网络的大多数参数，其性能也往往与学习所有参数的性能相当。讨论了深度神经网络这一有趣特性的含义，并提出了利用它来创建更强大的表示的方法。
英文摘要：
Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme Learning Machines, it has been suggested to set the first layer of a network to fixed random values instead of learning it. In this paper, we propose to take this approach a step further and fix almost all layers of a deep convolutional neural network, allowing only a small portion of the weights to be learned. As our experiments show, fixing even the majority of the parameters of the network often results in performance which is on par with the performance of learning all of them. The implications of this intriguing property of deep neural networks are discussed and we suggest ways to harness it to create more robust representations.
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。
