5,443
个编辑
更改
→基于离散方法计算神经网络层间EI
[[文件:互信息EI.png|500x500像素|thumb|center|MNIST和Iris任务中训练集和测试集的损失函数变化，引自<ref>Scythia Marrow, Eric J. Michaud, and Erik Hoel. Examining the Causal Structures of Deep Neural Networks Using Information Theory. In Entropy, volume 22, pages 1429, 2020.</ref>]]<br>
[[文件:互信息EI.png|500x500像素|thumb|center|MNIST和Iris任务中训练集和测试集的损失函数变化，引自<ref>Scythia Marrow, Eric J. Michaud, and Erik Hoel. Examining the Causal Structures of Deep Neural Networks Using Information Theory. In Entropy, volume 22, pages 1429, 2020.</ref>]]<br>
=基于连续方法观察神经网络EI变化=
=基于连续方法观察神经网络EI变化=