Towards Programming Adaptive Linear Neural Networks Through Chemical Reaction Networks

TL;DR

This paper presents a method to program adaptive linear neural networks using chemical reaction networks, enabling automatic computation with potential applications in synthetic biology and molecular computing.

Contribution

It introduces a novel approach to implement ALNNs via CRNs with mass-action kinetics, including programming of forward and backpropagation and the permeation walls technique.

Findings

Constructed a CRN that functions as an ALNN with automatic computation.

Provided theoretical analysis supporting the CRN design.

Case study demonstrating the practical potential of the approach.

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.