Towards Understanding Normalization in Neural ODEs

Abstract

Normalization is an important and vastly investigated technique in deep learning. However, its role for Ordinary Differential Equation based networks (neural ODEs) is still poorly understood. This paper investigates how different normalization techniques affect the performance of neural ODEs. Particularly, we show that it is possible to achieve 93% accuracy in the CIFAR-10 classification task, and to the best of our knowledge, this is the highest reported accuracy among neural ODEs tested on this problem.

References in corpus (5)

• Spectral Normalization for Generative Adversarial Networks
• Differentiable Learning-to-Normalize via Switchable Normalization
• ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
• Recurrent Batch Normalization
• ANODEV2: A Coupled Neural ODE Evolution Framework

Cited by in corpus (5)

• Normalization Techniques in Training DNNs: Methodology, Analysis and Application
• Momentum Residual Neural Networks
• Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs
• Inverse modified differential equations for discovery of dynamics
• Follow the bisector: a simple method for multi-objective optimization