Recurrent neural chemical reaction networks trained to switch dynamical behaviours through learned bifurcations

TL;DR

This paper demonstrates that recurrent neural chemical reaction networks (RNCRNs) can be trained to exhibit bifurcations and switch between different dynamical behaviors, mimicking natural chemical systems' transitions.

Contribution

The authors introduce methods for training RNCRNs to reproduce bifurcations and complex behaviors without explicit bifurcation data, including an ODE-free training algorithm for designer oscillations.

Findings

RNCRNs can inherit bifurcations from smooth ODEs.

RNCRNs can learn to switch behaviors across parameter space.

An ODE-free training algorithm enables designer oscillations.

Abstract

Both natural and synthetic chemical systems not only exhibit a range of non-trivial dynamics, but also transition between qualitatively different dynamical behaviours as environmental parameters change. Such transitions are called bifurcations. Here, we show that recurrent neural chemical reaction networks (RNCRNs), a class of chemical reaction networks based on recurrent artificial neural networks that can be trained to reproduce a given dynamical behaviour, can also be trained to exhibit bifurcations. First, we show that RNCRNs can inherit some bifurcations defined by smooth ordinary differential equations (ODEs). Second, we demonstrate that the RNCRN can be trained to infer bifurcations that allow it to approximate different target behaviours within different regions of parameter space, without explicitly providing the bifurcation itself in the training. These behaviours can be specified using target ODEs that are discontinuous with respect to the parameters, or even simply by specifying certain desired dynamical features in certain regions of the parameter space. To achieve the latter, we introduce an ODE-free algorithm for training the RNCRN to display designer oscillations, such as a heart-shaped limit cycle or two coexisting limit cycles.