Training DNA Perceptrons via Fractional Coding

TL;DR

This paper introduces a novel molecular training method for DNA perceptrons using fractional coding, enabling the synthesis of reactions for training neural networks at the molecular level.

Contribution

It presents a new molecular scaler and a training approach for DNA perceptrons based on fractional coding and modified backpropagation equations.

Findings

Proposed a molecular scaler for multiplication greater than 1.

Developed a training method for DNA perceptrons using fractional coding.

Established a link between stochastic logic and molecular computing.

Abstract

This paper describes a novel approach to synthesize molecular reactions to train a perceptron, i.e., a single-layered neural network, with sigmoidal activation function. The approach is based on fractional coding where a variable is represented by two molecules. The synergy between fractional coding in molecular computing and stochastic logic implementations in electronic computing is key to translating known stochastic logic circuits to molecular computing. In prior work, a DNA perceptron with bipolar inputs and unipolar output was proposed for inference. The focus of this paper is on synthesis of molecular reactions for training of the DNA perceptron. A new molecular scaler that performs multiplication by a factor greater than 1 is proposed based on fractional coding. The training of the perceptron proposed in this paper is based on a modified backpropagation equation as the exact equation cannot be easily mapped to molecular reactions using fractional coding.