Temporal Weights

TL;DR

This paper introduces Temporal Weights, a dynamic weight model inspired by biological synapses, integrated with Neural ODEs to improve temporal modeling in neural networks, leading to better performance and efficiency on time series data.

Contribution

It proposes a novel dynamic weight mechanism called Temporal Weights using Neural ODEs, enhancing temporal sequence modeling in neural networks.

Findings

Improved performance on sparse, irregular time series datasets.

Smaller models with higher data efficiency.

Effective modeling of temporal dynamics over sequence length and scale.

Abstract

In artificial neural networks, weights are a static representation of synapses. However, synapses are not static, they have their own interacting dynamics over time. To instill weights with interacting dynamics, we use a model describing synchronization that is capable of capturing core mechanisms of a range of neural and general biological phenomena over time. An ideal fit for these Temporal Weights (TW) are Neural ODEs, with continuous dynamics and a dependency on time. The resulting recurrent neural networks efficiently model temporal dynamics by computing on the ordering of sequences, and the length and scale of time. By adding temporal weights to a model, we demonstrate better performance, smaller models, and data efficiency on sparse, irregularly sampled time series datasets.