Automatic Implementation of Neural Networks Through Reaction Networks—Part II: Error Analysis

Bibliographic Details
Title: Automatic Implementation of Neural Networks Through Reaction Networks—Part II: Error Analysis
Authors: Yuzhen Fan, Xiaoyu Zhang, Chuanhou Gao, Denis Dochain
Source: IEEE Transactions on Automatic Control. 70:6372-6387
Publication Status: Preprint
Publisher Information: Institute of Electrical and Electronics Engineers (IEEE), 2025.
Publication Year: 2025
Subject Terms: Mathematics - Dynamical Systems
Description: This paired article aims to develop an automated and programmable biochemical fully connected neural network (BFCNN) with solid theoretical support. In Part I, a concrete design for BFCNN is presented, along with the validation of the effectiveness and exponential convergence of computational modules. In this article, we establish the framework for specifying the realization errors by monitoring the errors generated from approaching equilibrium points in individual modules, as well as their vertical propagation from upstream modules and horizontal accumulation from previous iterations. Ultimately, we derive the general error upper bound formula for any iteration and illustrate its exponential convergence order with respect to the phase length of the utilized chemical oscillator. The numerical experiments, based on the classification examples, reveal the tendency of total errors related to both the phase length and iteration number.
Document Type: Article
ISSN: 2334-3303
0018-9286
DOI: 10.1109/tac.2025.3574364
Access URL: http://arxiv.org/abs/2401.07077
Rights: IEEE Copyright
Accession Number: edsair.doi.dedup.....8ff80f935814ee57298c4a23e95721db
Database: OpenAIRE
Description
ISSN:23343303
00189286
DOI:10.1109/tac.2025.3574364