Closed-form continuous-time neural networks

doi:10.1038/s42256-022-00556-7

2022-11-15

DOI：10.1038/s42256-022-00556-7

原文链接

原文求助

摘要

En 中文

Physical dynamical processes can be modelled with differential equations that may be solved with numerical approaches, but this is computationally costly as the processes grow in complexity. In a new approach, dynamical processes are modelled with closed-form continuous-depth artificial neural networks. Improved efficiency in training and inference is demonstrated on various sequence modelling tasks including human action recognition and steering in autonomous driving. Continuous-time neural networks are a class of machine learning systems that can tackle representation learning on spatiotemporal decision-making tasks. These models are typically represented by continuous differential equations. However, their expressive power when they are deployed on computers is bottlenecked by numerical differential equation solvers. This limitation has notably slowed down the scaling and understanding of numerous natural physical phenomena such as the dynamics of nervous systems. Ideally, we would circumvent this bottleneck by solving the given dynamical system in closed form. This is known to be intractable in general. Here, we show that it is possible to closely approximate the interaction between neurons and synapses-the building blocks of natural and artificial neural networks-constructed by liquid time-constant networks efficiently in closed form. To this end, we compute a tightly bounded approximation of the solution of an integral appearing in liquid time-constant dynamics that has had no known closed-form solution so far. This closed-form solution impacts the design of continuous-time and continuous-depth neural models. For instance, since time appears explicitly in closed form, the formulation relaxes the need for complex numerical solvers. Consequently, we obtain models that are between one and five orders of magnitude faster in training and inference compared with differential equation-based counterparts. More importantly, in contrast to ordinary differential equation-based continuous networks, closed-form networks can scale remarkably well compared with other deep learning instances. Lastly, as these models are derived from liquid networks, they show good performance in time-series modelling compared with advanced recurrent neural network models.

Keyword:

APPROXIMATION

STABILITY