Exploring variability and quantization effects in artificial neural networks using the MNIST dataset

IF 1.4 4区物理与天体物理 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC

Solid-state Electronics Pub Date : 2026-02-01 Epub Date: 2025-12-04 DOI:10.1016/j.sse.2025.109296

Alan Blumenstein , Eduardo Pérez , Christian Wenger , Nadine Dersch , Alexander Kloes , Benjamín Iñíguez , Mike Schwarz

{"title":"Exploring variability and quantization effects in artificial neural networks using the MNIST dataset","authors":"Alan Blumenstein , Eduardo Pérez , Christian Wenger , Nadine Dersch , Alexander Kloes , Benjamín Iñíguez , Mike Schwarz","doi":"10.1016/j.sse.2025.109296","DOIUrl":null,"url":null,"abstract":"<div><div>This paper investigates the impact of introducing variability to trained neural networks and examines the effects of variability and quantization on network accuracy. The study utilizes the MNIST dataset to evaluate various Multi-Layer Perceptron configurations: a baseline model with a Single-Layer Perceptron and an extended model with multiple hidden nodes. The effects of Cycle-to-Cycle variability on network accuracy are explored by varying parameters such as the standard deviation to simulate dynamic changes in network weights. In particular, the performance differences between the Single-Layer Perceptron and the Multi-Layer Perceptron with hidden layers are analyzed, highlighting the network’s robustness to stochastic perturbations. These results provide insights into the effects of quantization and network architecture on accuracy under varying levels of variability.</div></div>","PeriodicalId":21909,"journal":{"name":"Solid-state Electronics","volume":"232 ","pages":"Article 109296"},"PeriodicalIF":1.4000,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Solid-state Electronics","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0038110125002412","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/12/4 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

This paper investigates the impact of introducing variability to trained neural networks and examines the effects of variability and quantization on network accuracy. The study utilizes the MNIST dataset to evaluate various Multi-Layer Perceptron configurations: a baseline model with a Single-Layer Perceptron and an extended model with multiple hidden nodes. The effects of Cycle-to-Cycle variability on network accuracy are explored by varying parameters such as the standard deviation to simulate dynamic changes in network weights. In particular, the performance differences between the Single-Layer Perceptron and the Multi-Layer Perceptron with hidden layers are analyzed, highlighting the network’s robustness to stochastic perturbations. These results provide insights into the effects of quantization and network architecture on accuracy under varying levels of variability.

查看原文本刊更多论文

利用MNIST数据集探索人工神经网络的可变性和量化效应

本文研究了将可变性引入训练神经网络的影响，并考察了可变性和量化对网络精度的影响。该研究利用MNIST数据集来评估各种多层感知器配置：单层感知器的基线模型和具有多个隐藏节点的扩展模型。通过改变标准偏差等参数来模拟网络权值的动态变化，探讨了周期到周期的可变性对网络精度的影响。特别地，分析了单层感知器和隐藏层多层感知器的性能差异，突出了网络对随机扰动的鲁棒性。这些结果为量化和网络架构在不同可变性水平下对准确性的影响提供了见解。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Solid-state Electronics 物理-工程：电子与电气

CiteScore

3.00

自引率

5.90%

发文量

212

审稿时长

3 months

期刊介绍： It is the aim of this journal to bring together in one publication outstanding papers reporting new and original work in the following areas: (1) applications of solid-state physics and technology to electronics and optoelectronics, including theory and device design; (2) optical, electrical, morphological characterization techniques and parameter extraction of devices; (3) fabrication of semiconductor devices, and also device-related materials growth, measurement and evaluation; (4) the physics and modeling of submicron and nanoscale microelectronic and optoelectronic devices, including processing, measurement, and performance evaluation; (5) applications of numerical methods to the modeling and simulation of solid-state devices and processes; and (6) nanoscale electronic and optoelectronic devices, photovoltaics, sensors, and MEMS based on semiconductor and alternative electronic materials; (7) synthesis and electrooptical properties of materials for novel devices.