Towards Programming Adaptive Linear Neural Networks Through Chemical Reaction Networks

2022/04/07 by Fan, Yuzhen, Zhang, Xiaoyu, Gao, Chuanhou
#Dynamical Systems (math.DS) #FOS: Mathematics

paper · doi:10.48550/arxiv.2204.03168

Abstract

This paper is concerned with programming adaptive linear neural networks (ALNNs) using chemical reaction networks (CRNs) equipped with mass-action kinetics. Through individually programming the forward propagation and the backpropagation of ALNNs, and also utilizing the permeation walls technique, we construct a powerful CRN possessing the function of ALNNs, especially having the function of automatic computation. We also provide theoretical analysis and a case study to support our construction. The results will have potential implications for the developments of synthetic biology, molecular computer and artificial intelligence.

Related

• Automatic Implementation of Neural Networks through Reaction Networks -- Part I: Circuit Design and Convergence Analysis
• Neural CRNs: A Natural Implementation of Learning in Chemical Reaction Networks
• Noise-robust chemical reaction networks training artificial neural networks
• On reaction network implementations of neural networks
• Differentiable Programming of Chemical Reaction Networks