Stateful ODE-Nets using Basis Function Expansions
The recently-introduced class of ordinary differential equation networks (ODE-Nets) establishes a fruitful connection between deep learning and dynamical systems. In this work, we reconsider formulations of the weights as continuous-in-depth functions using linear combinations of basis functions whi...
Saved in:
Main Authors | , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
20.06.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The recently-introduced class of ordinary differential equation networks
(ODE-Nets) establishes a fruitful connection between deep learning and
dynamical systems. In this work, we reconsider formulations of the weights as
continuous-in-depth functions using linear combinations of basis functions
which enables us to leverage parameter transformations such as function
projections. In turn, this view allows us to formulate a novel stateful
ODE-Block that handles stateful layers. The benefits of this new ODE-Block are
twofold: first, it enables incorporating meaningful continuous-in-depth batch
normalization layers to achieve state-of-the-art performance; second, it
enables compressing the weights through a change of basis, without retraining,
while maintaining near state-of-the-art performance and reducing both inference
time and memory footprint. Performance is demonstrated by applying our stateful
ODE-Block to (a) image classification tasks using convolutional units and (b)
sentence-tagging tasks using transformer encoder units. |
---|---|
DOI: | 10.48550/arxiv.2106.10820 |