[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123782-en":3,"doc-seo-123782-105":29,"detail-sidebar-cat-0-en-105":90},{"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":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},123782,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","How to Leverage Machine Learning Interpretability and Explainability to Generate Hypotheses in Cognitive Psychology","This paper outlines a cognitive science research program that uses machine learning (ML) to generate new hypotheses about human cognition. Instead of treating interpretability and explainability as algorithm-only properties, it reframes them as psychological constructs. Leveraging mathematical characteristics of ML methods—especially membership in Rashomon sets—enables parsimonious reasoning about inferential structure in cognitive tasks. The proposal is illustrated with clustering models for exploratory data analysis and followed by philosophical limitations.","UC Merced  \nProceedings of the Annual Meeting of the Cognitive Science Society  \nTitle  \nHow to Leverage Machine Learning Interpretability and Explainability to Generate Hypotheses in Cognitive Psychology  \nPermalink  \n[https://escholarship.org/uc/item/52s0d3dn](https://escholarship.org/uc/item/52s0d3dn)  \nJournal  \nProceedings of the Annual Meeting of the Cognitive Science Society, 45(45)  \nAuthors  \nFedyk, Mark  \nRay, Monika  \nPublication Date  \n2023  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nHow to Leverage Machine Learning Interpretability and Explainability to Generate Hypotheses in Cognitive Psychology  \nMark Fedyk ([mfedyk@udavis.edu](mfedyk@udavis.edu))  \nDepartment of Internal Medicine, University of California, Davis  \n4150 V St, Sacramento, CA 95817  \nMonika Ray ([mray@ucdavis.edu](mray@ucdavis.edu))  \nDepartment of Internal Medicine, University of California, Davis  \n4150 V St, Sacramento, CA 95817  \nAbstract  \nThis paper describes the principles of a research programme for cognitive science that exploits recent developments in machine learning (ML) to generate novel hypotheses about the structure of human cognition. Current debate over the interpretability and explainability algorithms usually focuses on the properties of the algorithms themselves in virtue of which they are either interpretable or explainable. However, we argue that there is value in conceptualizing these categories as inherently psychological constructs. Given certain mathematical features of machine learning algorithms – specifically, that many useful ML algorithms are members of Rashomon sets – it is possible to exploit their utility to reason using a principle of parsimony about the inferential structure of certain human cognitive tasks. Algorithms that do something the human mind can do, and are both interpretable and explicable could be, we shall argue, inferential homologues of certain core cognitive processes. We illustrate this proposal with an example drawn from clustering models used in exploratory data analysis, and then conclude with a discussion of some of the philosophical limitations of our proposal.  \nKeywords: philosophy of cognitive science, interpretability, explainability, philosophy of machine learning, concept acquisition, ethology, comparative psychology, naturalistic epistemology, cognitive psychology  \nScientific Background and Context  \nThe evolutionary pressures of natural selection do not, as a matter of principle, conserve the most optimal, efficient, rational, or balanced solutions to adaptive behavioral problems (West-Eberhard, 2003) . There is therefore no general reason, given the evolutionary origins of the human cognitive system, to assume that the way the human mind forms concepts, abstracts categories from perceptual evidence, identifies causes and frames effects, makes inferences about future events, forms beliefs about hidden processes, reasons about the mind of other people is, from either a computational or mathematical or philosophical perspective, anywhere near optimal.  \nThe same reasoning applies in the other direction. There is no reason to assume that the cognitive processes which implement both those and other centrally important cognitive abilities are profoundly sub-optimal. At best, we are licensed to conclude that all these various cognitive capacities are  \nimperfectly useful, and that the utility of cognitive functions will vary across contexts.  \nBut this means it is not possible to make accurate predictions about the specific structure of human cognitive processes on a priori grounds – by defining a particular cognitive task, finding out what algorithms can be used to solve the task, and then identifying the most efficient of these, and concluding that those algorithms are (most probably) the ones which are implemented in the human cognitive system (Boyd, 2016; Fedyk, 2015) .  \nAn alternative approach finds i","cbCaibFqLWxLa75t","https://ap.wps.com/l/cbCaibFqLWxLa75t","pdf",370240,1,"English","en",105,"# Scientific Background and Context\n## Evolution, optimization, and cognitive utility\n## Why task-first algorithm comparisons fail\n## Comparative ethology and developmental parallels\n## Marr’s levels of description and the proposal","[{\"question\":\"What is the main goal of the research program described in the paper?\",\"answer\":\"To exploit recent machine learning developments to generate novel hypotheses about the structure of human cognition.\"},{\"question\":\"How does the paper reinterpret interpretability and explainability?\",\"answer\":\"It argues that interpretability and explainability should be understood as inherently psychological constructs, not only as properties of algorithms.\"},{\"question\":\"What mathematical feature of many ML algorithms does the paper rely on?\",\"answer\":\"It emphasizes that many useful ML algorithms are members of Rashomon sets, enabling reasoning using parsimony about inferential structure.\"}]","How to Leverage Machine Learning Interpretability and Explainability to Generate Hypotheses in Cognitive Psychology | PDF",1785818537,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"how-to-leverage-machine-learning-interpretability-and-explainability-to-generate-hypotheses-in-cognitive-psychology","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/how-to-leverage-machine-learning-interpretability-and-explainability-to-generate-hypotheses-in-cognitive-psychology/123782/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of the research program described in the paper?","Question",{"text":74,"@type":75},"To exploit recent machine learning developments to generate novel hypotheses about the structure of human cognition.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the paper reinterpret interpretability and explainability?",{"text":79,"@type":75},"It argues that interpretability and explainability should be understood as inherently psychological constructs, not only as properties of algorithms.",{"name":81,"@type":72,"acceptedAnswer":82},"What mathematical feature of many ML algorithms does the paper rely on?",{"text":83,"@type":75},"It emphasizes that many useful ML algorithms are members of Rashomon sets, enabling reasoning using parsimony about inferential structure.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]