[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118009-en":3,"doc-seo-118009-105":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":4,"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},118009,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Does Machine Learning Replicate the Uncanny Valley? - An Example using FaceNet","Androids that strongly but imperfectly resemble humans in shape can elicit negative emotions in people, a phenomenon known as the “uncanny valley,” replicated in laboratory experiments. With recent advances in face recognition accuracy based on machine learning, this work examines whether machine learning can replicate uncanny valley effects. Using FaceNet, the study evaluates alignment between machine similarity judgments and human evaluation and analyzes which visual regions drive decisions.","UC Merced  \nProceedings of the Annual Meeting of the Cognitive Science Society  \nTitle  \nDoes Machine Learning Replicate the Uncanny Valley? An Example using FaceNet  \nPermalink  \n[https://escholarship.org/uc/item/57v063mh](https://escholarship.org/uc/item/57v063mh)  \nJournal  \nProceedings of the Annual Meeting of the Cognitive Science Society, 45(45)  \nAuthors  \nImaizumi, Taku  \nLi, Lu  \nUeda, Kazuhiro  \nPublication Date  \n2023  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nDoes Machine Learning Replicate the Uncanny Valley? An Example using FaceNet  \nTaku Imaizumi ([taku-imaizumi605@g.ecc.u-tokyo.ac.jp](taku-imaizumi605@g.ecc.u-tokyo.ac.jp))  \nGraduate School of Interdisciplinary Information Studies, The University of Tokyo  \n7-3-1, Hongo, Bunkyo-Ku, Tokyo 113-0033, Japan  \nLu Li ([2000lilu0317@g.ecc.u-tokyo.ac.jp](2000lilu0317@g.ecc.u-tokyo.ac.jp))  \nGraduate School of Interdisciplinary Information Studies, The University of Tokyo  \n7-3-1, Hongo, Bunkyo-Ku, Tokyo 113-0033, Japan  \nKazuhiro Ueda ([ueda@g.ecc.u-tokyo.ac.jp](ueda@g.ecc.u-tokyo.ac.jp))  \nGraduate School of Arts and Sciences, The University of Tokyo  \n3-8-1, Komaba, Meguro-Ku, Tokyo 153-0902, Japan  \nAbstract  \nAndroids that strongly but imperfectly resemble humans in shape can elicit negative emotions in people, a phenomenon known as the \"uncanny valley,\" which has been replicated in laboratory experiments. Recently, the accuracy of face recognition utilizing machine learning has increased, raising the question of whether machine learning can replicate the uncanny valley effect. In this study, using FaceNet as a representative face recognition algorithm, we examined the similarity of face recognition to human evaluation and its replication of the uncanny valley. The results revealed a strong correlation between machine learning and human evaluation of human-like shapes. However, because the evaluations recorded were significantly disparate for some objects, it is evident that only certain aspects of the uncanny valley were replicated. Furthermore, visualization of the activation maps suggests that localized regions, such as the mouth and chin, acted as the basis for judgment. These findings support the idea that human and machine learning have distinct areas of attention, as well as the categorization ambiguity hypothesis, and perceptual mismatch hypothesis in the study of the uncanny valley effect.  \nKeywords: face recognition; machine learning; FaceNet; uncanny valley; Grad-CAM  \nIntroduction  \nUncanny Valley  \nWhen an artifact, such as a robot or agent, resembles but does not fully emulate the human form, the viewer may have a negative perception of it. This phenomenon, referred to as the\"uncanny valley\" (Mori, 1970; Mori, MacDorman & Kageki, 2012) has been considered a challenge to be overcome in facilitating communication between humans and robots (MacDorman et al., 2005) . Understanding the mechanism of the uncanny valley contributes not only to the domains of robotics and human-agent interaction by fostering the creation of favorable agents, but also to cognitive science by facilitating laboratory experiments using such agents (Piwek, McKay & Pollick, 2014; de Borst & de Gelder, 2016) .  \nThe uncanny valley has been chiefly investigated from two perspectives: the categorization ambiguity hypothesis, and the perceptual mismatch hypothesis (Kätsyri, Förger,  \nFigure 1 : Reproduction of the uncanny valley as reported by Mathur et al. (2020). Fitting and charting were performed by the authors.  \nMäkäräinen & Takala, 2015) . The categorization ambiguity hypothesis posits that the uncanny valley arises due to anaversion to objects that straddle the boundary between human and artifact, while the perceptual mismatch hypothesis contends that negative affinity is caused by an inconsistency between the human-likeness levels of specific sensory cues.  \nAlthough the uncanny valley theory i","cbCair9PfKvoJGpa","https://ap.wps.com/l/cbCair9PfKvoJGpa","pdf",779887,1,"English","en",105,"# Introduction\n## Uncanny Valley\n## Machine Learning and Face Recognition","[{\"question\":\"What is the uncanny valley, and why does it matter for human-agent interaction?\",\"answer\":\"The uncanny valley describes negative perception when an artifact resembles humans but does not fully emulate human form. Understanding its mechanism helps guide the creation of more favorable agents and supports cognitive-science experiments using such agents.\"},{\"question\":\"How does this study test whether machine learning replicates the uncanny valley?\",\"answer\":\"The study uses FaceNet as a face recognition algorithm and compares machine recognition similarity with human evaluation. It then examines how closely the machine results reproduce the uncanny valley pattern.\"},{\"question\":\"What do the results suggest about what drives judgments in uncanny valley perception?\",\"answer\":\"The findings show a strong correlation with human evaluation, but disparities for some objects indicate only certain aspects are replicated. Visualization of activation maps suggests localized regions like the mouth and chin contribute to the judgments, supporting distinct attention and categorization/perceptual mismatch explanations.\"}]","Does Machine Learning Replicate the Uncanny Valley? - An Example using FaceNet | PDF",1785680737,20,{"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},"does-machine-learning-replicate-the-uncanny-valley-an-example-using-facenet","",{"@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/does-machine-learning-replicate-the-uncanny-valley-an-example-using-facenet/118009/",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","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the uncanny valley, and why does it matter for human-agent interaction?","Question",{"text":74,"@type":75},"The uncanny valley describes negative perception when an artifact resembles humans but does not fully emulate human form. Understanding its mechanism helps guide the creation of more favorable agents and supports cognitive-science experiments using such agents.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does this study test whether machine learning replicates the uncanny valley?",{"text":79,"@type":75},"The study uses FaceNet as a face recognition algorithm and compares machine recognition similarity with human evaluation. It then examines how closely the machine results reproduce the uncanny valley pattern.",{"name":81,"@type":72,"acceptedAnswer":82},"What do the results suggest about what drives judgments in uncanny valley perception?",{"text":83,"@type":75},"The findings show a strong correlation with human evaluation, but disparities for some objects indicate only certain aspects are replicated. Visualization of activation maps suggests localized regions like the mouth and chin contribute to the judgments, supporting distinct attention and categorization/perceptual mismatch explanations.","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"]