Correlated Weights in Infinite Limits of Deep Convolutional Neural Networks

Abstract

Infinite width limits of deep neural networks often have tractable forms. They have been used to analyse the behaviour of finite networks, as well as being useful methods in their own right. When investigating infinitely wide convolutional neural networks (CNNs), it was observed that the correlations arising from spatial weight sharing disappear in the infinite limit. This is undesirable, as spatial correlation is the main motivation behind CNNs. We show that the loss of this property is not a consequence of the infinite limit, but rather of choosing an independent weight prior. Correlating the weights maintains the correlations in the activations. Varying the amount of correlation interpolates between independent-weight limits and mean-pooling. Empirical evaluation of the infinitely wide network shows that optimal performance is achieved between the extremes, indicating that correlations can be useful.

Accepted for the 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021)

References in corpus (7)

• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Deep Neural Networks as Gaussian Processes
• On Exact Computation with an Infinitely Wide Neural Net
• Convolutional Kernel Networks
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
• Steps Toward Deep Kernel Methods from Infinite Neural Networks
• Neural Kernels Without Tangents

Cited by in corpus (2)

• Bayesian Neural Network Priors Revisited
• Dependence between Bayesian neural network units