Neural Tangent Kernel Analysis of Deep Narrow Neural Networks

02/07/2022
by   Jongmin Lee, et al.
0

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

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset