Recurrent Neural Networks (RNNs) are effective tools for processing sequential data.

State-space models have gained popularity in sequence modelling due to their simple and efficient network structures. However, the absence of nonlinear activation along the temporal direction limits the model's capacity.

A promising way to extract computational principles from these large datasets is to train data-constrained recurrent neural networks (dRNNs).

The contributions of this paper are as follows (Figure 1): 1.

Emergence of grid-like representations by training recurrent neural networks to perform spatial localization.

This led to successful applications of Neural ODEs in machine learning.

Such models range broadly in both complexity and biological plausibility.