Approach to provide interpretability in machine learning models for image classification

Author:

Stadlhofer Anja,Mezhuyev Vitaliy

Abstract

AbstractOne of the main reasons why machine learning (ML) methods are not yet widely used in productive business processes is the lack of confidence in the results of an ML model. To improve the situation, interpretability methods may be used, which provide insight into the internal structure of an ML model, and criteria, based on which the model makes a certain prediction. This paper aims to consider the state of the art in interpretability methods and apply the selected methods to an industrial use case. Two methods, called LIME and SHAP, were selected from the literature and next implemented in the use case for image classification using a convolutional neural network. The research methodology consists of three parts, the first is the literature analysis, followed by the practical implementation of an ML model for image classification and the subsequent application of the interpretability methods, and the third part is a multi-criteria comparison of selected LIME and SHAP methods. This work enables companies to select the most effective interpretability method according to their use case and also to increase companies’ motivation for using ML.

Publisher

Springer Science and Business Media LLC

Reference37 articles.

1. Oks SJ, Frietzsche A, Lehmann C (2016) The digitalization of industry from a strategic perspective. In: Presented at the R&D management conference from science to society: innovation and value creation, Cambridge, United Kingdom

2. Bonaccorso G (2017) A gentle introduction to machine learning. In: Machine learning algorithms—a reference guide to popular algorithms for data science and machine learning, Birmingham, United Kingdom, pp 6–9

3. Zhang X (2020) Machine learning. A matrix algebra approach to artificial intelligence, 1st edn. Springer, Singapore, pp 223–224

4. Dosilovic FK, Brcic M, Hlupic N (2018) Explainable artificial intelligence: a survey. In: Presented at the 41st international convention on MIPRO, Opatija, Croatia, pp 210–215

5. Bhatt U et al (2019) Explainable machine learning in deployment. In: Presented at proceedings of the 2020 conference on fairness, accountability and transparency, Cambridge, United Kingdom

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Pretrained Deep Learning Models to Reduce Data Needed for Quality Assurance;Proceedings of the 2024 10th International Conference on Computer Technology Applications;2024-05-15

2. Approaches for data collection and process standardization in smart manufacturing: Systematic literature review;Journal of Industrial Information Integration;2024-03

3. CapStyleBERT: Incorporating Capitalization and Style Information into BERT for Enhanced resumes parsing;Proceedings of the 2024 13th International Conference on Software and Computer Applications;2024-02

4. Principles of Machine Learning;Artificial Intelligence in Medical Imaging Technology;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3