[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117012-en":3,"doc-seo-117012-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117012,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Evolutionary Approaches to Explainable Machine Learning","Machine learning increasingly powers high-stakes decisions, yet black-box behavior limits accountability and trust. Explainable AI (XAI) and explainable machine learning (XML) address this by enabling humans to understand predictions, assess bias and failures, validate and debug models, support regulatory compliance, and improve human-machine interaction. The chapter surveys existing XAI/XML techniques and then highlights how evolutionary computing can contribute to explanation generation, explanation-quality assessment, and future research directions.","arXiv :2306 . 14786v 1 [ cs .AI] 23 Jun 2023  \nEvolutionary Approaches to Explainable Machine Learning  \nRyan Zhou and Ting Hu  \nAbstract Machine learning models are increasingly being used in critical sectors, but their black-box nature has raised concerns about accountability and trust. The field of explainable artificial intelligence (XAI) or explainable machine learning (XML) has emerged in response to the need for human understanding of these models. Evolutionary computing, as a family of powerful optimization and learning tools, has significant potential to contribute to XAI/XML. In this chapter, we provide a brief introduction to XAI/XML and review various techniques in current use for explaining machine learning models. We then focus on how evolutionary computing can be used in XAI/XML, and review some approaches which incorporate EC techniques. We also discuss some open challenges in XAI/XML and opportunities for future research in this field using EC. Our aim is to demonstrate that evolutionary computing is well-suited for addressing current problems in explainability, and to encourage further exploration of these methods to contribute to the development of more transparent, trustworthy and accountable machine learning models.  \n1 Introduction  \nAs the use of machine learning models becomes increasingly widespread in various domains, including critical sectors of society such as finance and healthcare, there is a growing need for human understanding of such models. Although machine learning can detect complex patterns and relationships in data, decisions based on the predictions made by these models can have real-world impacts on human lives. The use of machine learning models in high-stakes applications such as medicine, job hiring, and criminal justice has raised concerns about the fairness, transparency, and accountability of these models. Therefore, it is essential not only to develop accurate prediction models but also to understand and explain how these predictions are being made.  \nSchool of Computing, Queen's University, Kingston, ON K7L 2N8, Canada  \n2 Ryan Zhou and Ting Hu  \nThe field of explainable artificial intelligence (XAI) or explainable machine learning (XML) has emerged in response to this need [37] . XAI research aims to develop methods to explain the decisions, predictions, or recommendations made by machine learning models in a way that is understandable to humans. These explanations act as a foundation to build trust and improve the robustness of a model by highlighting biases and failures, allow researchers to better understand, validate and debug the model, ensure compliance with regulations, and improve humanmachine interaction by giving users a better understanding of when they can rely on a model's decisions.  \nIn this book chapter, we aim to provide an overview of XAI/XML and the role of evolutionary computing (EC) in this field. In Section 2, we introduce the concept of XML and review current techniques used in the field. In Section 3, we will focus on evolutionary techniques for explaining machine learning models. Specifically, we will cover data visualization, feature selection and engineering, local and global explanations, counter-factual and adversarial examples. We will also discuss evolutionary methods designed specifically for explaining deep learning models, as well as evolutionary methods for assessing the quality of explanations themselves. In Section 4, we identify some challenges remaining in the field of XAI/XML and discuss future opportunities for incorporating EC. Finally, Section 5 provides concluding remarks for the chapter.  \n2 Explainable Machine Learning  \nExplainability and the fields of XAI/XML are concerned with extracting insights from machine learning models in order to make them more transparent, interpretable and understandable to humans. The goal of XAI/XML is to develop methods that can provide clear explanations of the decision-making process and enable humans to underst","cbCaiiuda7JscJh6","https://ap.wps.com/l/cbCaiiuda7JscJh6","pdf",221710,1,20,"English","en",105,"# Introduction\n## Explainable Machine Learning\n## Interpretability vs. Explainability","[{\"question\":\"What problem does explainable machine learning (XML) address?\",\"answer\":\"XML addresses the difficulty of understanding black-box predictions in high-stakes settings, where fairness, transparency, and accountability are needed.\"},{\"question\":\"What is the difference between interpretability and explainability?\",\"answer\":\"Interpretability focuses on how transparently and directly a human can trace a model’s decision process, while explainability focuses on providing human-understandable reasons for predictions even when exact logic cannot be traced.\"},{\"question\":\"How can evolutionary computing contribute to XAI/XML?\",\"answer\":\"Evolutionary computing can be used to support explanation approaches, including techniques such as feature selection and engineering, visualization, local and global explanations, and methods that assess explanation quality.\"}]","Evolutionary Approaches to Explainable Machine Learning | PDF",1785673078,50,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"evolutionary-approaches-to-explainable-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/evolutionary-approaches-to-explainable-machine-learning/117012/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does explainable machine learning (XML) address?","Question",{"text":75,"@type":76},"XML addresses the difficulty of understanding black-box predictions in high-stakes settings, where fairness, transparency, and accountability are needed.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the difference between interpretability and explainability?",{"text":80,"@type":76},"Interpretability focuses on how transparently and directly a human can trace a model’s decision process, while explainability focuses on providing human-understandable reasons for predictions even when exact logic cannot be traced.",{"name":82,"@type":73,"acceptedAnswer":83},"How can evolutionary computing contribute to XAI/XML?",{"text":84,"@type":76},"Evolutionary computing can be used to support explanation approaches, including techniques such as feature selection and engineering, visualization, local and global explanations, and methods that assess explanation quality.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":29,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]