{"id":3667,"date":"2025-09-22T18:32:53","date_gmt":"2025-09-22T18:32:53","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=3667"},"modified":"2025-09-22T18:32:53","modified_gmt":"2025-09-22T18:32:53","slug":"few-shot-characterisation-of-black-box-rf-fitting-with-gaussian-processes","status":"publish","type":"page","link":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/?page_id=3667","title":{"rendered":"Few-Shot Characterisation of Black-Box RF Fitting with Gaussian Processes"},"content":{"rendered":"\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Few\u2011Shot_Characterisation_of_Black\u2011Box_RF_Fitting_with_Gaussian_Processes.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of Few\u2011Shot_Characterisation_of_Black\u2011Box_RF_Fitting_with_Gaussian_Processes.\"><\/object><a id=\"wp-block-file--media-6e5ebe0b-f7a5-494a-be90-d87ceb462b45\" href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Few\u2011Shot_Characterisation_of_Black\u2011Box_RF_Fitting_with_Gaussian_Processes.pdf\">Few\u2011Shot_Characterisation_of_Black\u2011Box_RF_Fitting_with_Gaussian_Processes<\/a><a href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Few\u2011Shot_Characterisation_of_Black\u2011Box_RF_Fitting_with_Gaussian_Processes.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-6e5ebe0b-f7a5-494a-be90-d87ceb462b45\">Download<\/a><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Accurately characterising the performance of black-box RF demodulation pipelines normally<br>requires dense sweeps over many parameters, incurring high computational cost[1]. Gaussian<br>process (GP) surrogate models provide smooth interpolants and predictive uncertainty, enabling<br>efficient exploration[1]. This paper investigates how many targeted runs are needed to reconstruct a smooth performance field and whether the GP uncertainty estimates are well calibrated.<br>A synthetic two-dimensional performance function serves as the ground truth. We sample N<br>points uniformly at random, fit a GP to the observations and evaluate the root mean-squared error (RMSE) and mean predictive uncertainty on a dense grid. Results show that modest sample<br>sizes (N in the tens) yield low RMSE and that predictive uncertainty decays at a similar rate.<br>Calibration curves illustrate that the GP standard deviation provides reasonably accurate confidence intervals[2]. These findings support using few-shot GP characterisation for deployment<br>planning in RF systems.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Accurately characterising the performance of black-box RF demodulation pipelines normallyrequires dense sweeps over many parameters, incurring high computational cost[1]. Gaussianprocess (GP) surrogate models provide smooth interpolants and predictive uncertainty, enablingefficient exploration[1]. This paper investigates how many targeted runs are needed to reconstruct a smooth performance field and whether the GP uncertainty estimates are well calibrated.A&hellip;&nbsp;<\/p>\n","protected":false},"author":2,"featured_media":2705,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"class_list":["post-3667","page","type-page","status-publish","has-post-thumbnail","hentry"],"_links":{"self":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/3667","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3667"}],"version-history":[{"count":0,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/3667\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/media\/2705"}],"wp:attachment":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3667"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}