Noise-robust chemical reaction networks training artificial neural networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kang, Sunghwa, Kim, Jinsu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909351217725440
author Kang, Sunghwa
Kim, Jinsu
author_facet Kang, Sunghwa
Kim, Jinsu
contents Artificial neural networks (NNs) can be implemented using chemical reaction networks (CRNs), where the concentrations of species act as inputs and outputs. In such biochemical computing, noise-robust computing is crucial due to the intrinsic and extrinsic noise present in chemical reactions. Previously suggested CRNs for feed-forward networks often utilized the rectified linear unit (ReLU) or discrete activation functions. However, one concern in this case is the discontinuities of the derivatives of those non-smooth functions, which can cause significant noise disruption during backpropagation. In this study, we propose a CRN that performs both feed-forward and training processes using smooth activation functions to avoid discontinuities in the backpropagation. All reactions occur in a single pot, and the reactions for training are bimolecular. Our case studies on XOR, Iris, MNIST datasets, and a non-linear regression model demonstrate that computation via the CRN (i) maintains accuracy despite noise in the reaction rates and the concentration of species and (ii) is insensitive to the choice of the running time and the magnitude of the noise in comparison to NNs with a non-smooth activation function. This work presents a noise-robust CRN for full NN computation, including backpropagation, paving the way for more stable and efficient biochemical computing systems.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11919
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Noise-robust chemical reaction networks training artificial neural networks
Kang, Sunghwa
Kim, Jinsu
Molecular Networks
Emerging Technologies
Chemical Physics
92B05, 92B20
Artificial neural networks (NNs) can be implemented using chemical reaction networks (CRNs), where the concentrations of species act as inputs and outputs. In such biochemical computing, noise-robust computing is crucial due to the intrinsic and extrinsic noise present in chemical reactions. Previously suggested CRNs for feed-forward networks often utilized the rectified linear unit (ReLU) or discrete activation functions. However, one concern in this case is the discontinuities of the derivatives of those non-smooth functions, which can cause significant noise disruption during backpropagation. In this study, we propose a CRN that performs both feed-forward and training processes using smooth activation functions to avoid discontinuities in the backpropagation. All reactions occur in a single pot, and the reactions for training are bimolecular. Our case studies on XOR, Iris, MNIST datasets, and a non-linear regression model demonstrate that computation via the CRN (i) maintains accuracy despite noise in the reaction rates and the concentration of species and (ii) is insensitive to the choice of the running time and the magnitude of the noise in comparison to NNs with a non-smooth activation function. This work presents a noise-robust CRN for full NN computation, including backpropagation, paving the way for more stable and efficient biochemical computing systems.
title Noise-robust chemical reaction networks training artificial neural networks
topic Molecular Networks
Emerging Technologies
Chemical Physics
92B05, 92B20
url https://arxiv.org/abs/2410.11919