We present a differentiable formulation of abstract chemical reaction networks (CRNs) that can be trained to solve a variety of computational tasks. Chemical reaction networks are one of the most fundamental computational substrates used by nature. We study well-mixed single-chamber systems, as well as systems with multiple chambers separated by membranes, under mass-action kinetics. We demonstrate that differentiable optimisation, combined with proper regularisation, can discover non-trivial sparse reaction networks that can implement various sorts of oscillators and other chemical computing devices.

翻译：化学反应网络是大自然使用的最根本的计算基子之一。 我们研究混合的单细胞系统,以及由膜隔开的多室系统,在大规模运动动能学下。 我们证明,不同优化化,加上适当的正规化,可以发现非三角的稀有反应网络,可以使用各种振荡器和其他化学计算装置。