全连接层的谱修剪：基于特征值对节点进行排序
Spectral pruning of fully connected layers: ranking the nodes based on the eigenvalues
摘要：
神经网络的训练可以在谱空间中重新公式化，通过允许网络的特征值和特征向量作为优化的目标，而不是单独的权重。在这种情况下工作，我们表明，特征值可以用来排名内的合奏节点的重要性。事实上，我们将证明，根据节点的相关特征值对节点进行排序，可以实现有效的预处理和后处理修剪策略，以产生大规模紧凑的网络（就组成神经元的数量而言），其性能几乎不变。所提出的方法进行了测试，不同的架构，只有一个或多个隐藏层，并对不同的分类任务的普遍兴趣。
英文摘要：
Training of neural networks can be reformulated in spectral space, by allowing eigenvalues and eigenvectors of the network to act as target of the optimization instead of the individual weights. Working in this setting, we show that the eigenvalues can be used to rank the nodes' importance within the ensemble. Indeed, we will prove that sorting the nodes based on their associated eigenvalues, enables effective pre- and post-processing pruning strategies to yield massively compacted networks (in terms of the number of composing neurons) with virtually unchanged performance. The proposed methods are tested for different architectures, with just a single or multiple hidden layers, and against distinct classification tasks of general interest.
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。
