论文标题
深窄神经网络的神经切线内核分析
Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
论文作者
论文摘要
在分析过度参数化神经网络的训练动力学方面的最新进展主要集中在广泛的网络上，因此无法充分解决深度在深度学习中的作用。在这项工作中，我们介绍了第一个无限深层但狭窄的神经网络的训练保证。我们研究具有特定初始化的多层感知器（MLP）的无限深度极限，并使用NTK理论建立了可训练性保证。然后，我们将分析扩展到无限深的卷积神经网络（CNN），并进行简短的实验。
The tremendous recent progress in analyzing the training dynamics of overparameterized neural networks has primarily focused on wide networks and therefore does not sufficiently address the role of depth in deep learning. In this work, we present the first trainability guarantee of infinitely deep but narrow neural networks. We study the infinite-depth limit of a multilayer perceptron (MLP) with a specific initialization and establish a trainability guarantee using the NTK theory. We then extend the analysis to an infinitely deep convolutional neural network (CNN) and perform brief experiments.
