{"id":700,"date":"2024-10-21T15:01:26","date_gmt":"2024-10-21T15:01:26","guid":{"rendered":"https:\/\/mbic-auditorylab.nl\/home\/?p=700"},"modified":"2024-10-21T15:03:00","modified_gmt":"2024-10-21T15:03:00","slug":"new-preprint-on-ssrn-deciphering-the-transformation-of-sounds-into-meaning-insights-from-disentangling-intermediate-representations-in-sound-to-event-dnns","status":"publish","type":"post","link":"https:\/\/mbic-auditorylab.nl\/home\/new-preprint-on-ssrn-deciphering-the-transformation-of-sounds-into-meaning-insights-from-disentangling-intermediate-representations-in-sound-to-event-dnns\/","title":{"rendered":"New preprint in SSRN: Deciphering the Transformation of Sounds into Meaning: Insights from Disentangling Intermediate Representations in Sound-to-Event DNNs."},"content":{"rendered":"<p><span dir=\"ltr\" role=\"presentation\">In this new paper,we examine the nature of sound representations in intermediate layers of convolutional DNNs\u00a0 by means of <em>in silico<\/em> experiments involving a new sound data set of material and actions. Furthermore, by means of a new methodology based on invertible neural networks, we show that there is a causal relationship between these internal representations and the semantic model output.<br \/>\n<\/span><\/p>\n<p><span dir=\"ltr\" role=\"presentation\">Deciphering the Transformation of Sounds into Meaning: Insights from Disentangling Intermediate Representations in Sound-to-Event DNNs.\u00a0 <strong>Tim Dick<\/strong>, Alexia Briassouli, Enrique Hortal Quesada and Elia Formisano (2024) Available at SSRN: <a href=\"https:\/\/ssrn.com\/abstract=4979651\" target=\"_blank\" rel=\"noopener\">https:\/\/ssrn.com\/abstract=4979651<\/a>\u00a0or\u00a0<a class=\"textlink\" href=\"https:\/\/dx.doi.org\/10.2139\/ssrn.4979651\" target=\"_blank\" rel=\"noopener\">http:\/\/dx.doi.org\/10.2139\/ssrn.4979651<\/a><\/span><span dir=\"ltr\" role=\"presentation\">.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>In this new paper,we examine the nature of sound representations in intermediate layers of convolutional DNNs\u00a0 by means of in silico experiments involving a new sound data set of material and actions. Furthermore, by means of a new methodology based on invertible neural networks, we show that there is a causal relationship between these internal [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-700","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"acf":[],"_links":{"self":[{"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/posts\/700","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/comments?post=700"}],"version-history":[{"count":3,"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/posts\/700\/revisions"}],"predecessor-version":[{"id":704,"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/posts\/700\/revisions\/704"}],"wp:attachment":[{"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/media?parent=700"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/categories?post=700"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mbic-auditorylab.nl\/home\/wp-json\/wp\/v2\/tags?post=700"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}