{"id":153,"date":"2025-10-21T14:11:18","date_gmt":"2025-10-21T14:11:18","guid":{"rendered":"https:\/\/ykim.synology.me\/wordpress\/?page_id=153"},"modified":"2026-04-17T21:03:38","modified_gmt":"2026-04-18T02:03:38","slug":"data-science-and-ai-integration","status":"publish","type":"page","link":"https:\/\/ykim.synology.me\/wordpress\/job-capability__trashed\/data-science-and-ai-integration\/","title":{"rendered":"Data Science and AI Integration"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Experimental, AI\u2011assisted, data\u2011driven methodologies integrated into engineering platforms and supported by semiconductor, statistical, machine\u2011learning, and deep\u2011learning technologies to optimize semiconductor manufacturing across process, device, and yield development. The following are the key components of my work on AI\u2011Driven Engineering Platforms:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-theme-palette-3-color\">AI-assisted software<\/mark><\/strong>: AI-agent<\/li>\n\n\n\n<li><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-theme-palette-3-color\"><strong>AI-assisted data analysis<\/strong>:<\/mark> yield analysis enabling yield-aware design and yieldable process\/device\n<ul class=\"wp-block-list\">\n<li><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-theme-palette-3-color\">Machine Learning<\/mark>: PCA, SVM, Bayesian Optimization<\/li>\n\n\n\n<li><mark style=\"background-color:rgba(0, 0, 0, 0);color:#0000ff\" class=\"has-inline-color\">D<\/mark><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-theme-palette-3-color\">eep Learning:<\/mark> time-series data<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li><strong>Statistical data analysis<\/strong>: Gaussian, Poisson, Order statistics, Extreme Value Distribution<\/li>\n\n\n\n<li>(Semiconductor) <strong>Technology-based analysis<\/strong>: Device physics, Small circuit simulation, Error propagation, Monte Carlo Simulation, DOE\/RSM, Split-CV, Dielectric Conduction, Variability, BKM management, Soft\/hard yield<\/li>\n\n\n\n<li><strong>Full-stack web platform<\/strong> using WordPress, Flask, or <mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-theme-palette-6-color\">Next.js<\/mark><\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">The motivation for <strong>technology convergence<\/strong> that integrates semiconductor technology with data science is that this convergence is essential for technology-aware software that enables:<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>Advancing semiconductor technology<\/li>\n\n\n\n<li>Improving engineers\u2019 productivity<\/li>\n\n\n\n<li>Creating a more fulfilling work environment.<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">A <strong>technology\u2011aware software engineer<\/strong> can deliver this integration effectively, since domain\u2011aware development fits well with Agile and DevOps practices.<\/p>\n\n\n\n<div class=\"wp-block-group my-row-with-gap is-nowrap is-layout-flex wp-container-core-group-is-layout-8f761849 wp-block-group-is-layout-flex\">\n<img decoding=\"async\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/02\/20260206-Agile-methodology-UX-320x320px.png\" style=\"width:auto;height:200px\">\n\n\n\n<img decoding=\"async\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/01\/20260130-DevOps.png\" style=\"width:auto;height:200px\">\n<\/div>\n\n\n\n<p class=\"wp-block-paragraph\">A <strong>technology\u2011aware software<\/strong> <strong>tool <\/strong>provides several key benefits:<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><em>Helps engineers quickly learn the legacy knowledge from previous technologies<\/em><\/li>\n\n\n\n<li><em>Enables engineers to absorb leading\u2011edge technology more effectively<\/em><\/li>\n\n\n\n<li><em>Speeds up computational workflows<\/em><\/li>\n\n\n\n<li><em>Ensures work is performed in a standardized manner<\/em><\/li>\n\n\n\n<li><em>Standardizes data by serving as a de facto specification<\/em><\/li>\n\n\n\n<li><em>Needs continuous improvement as the technology evolves, with pros and cons.<\/em><\/li>\n<\/ol>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" style=\"margin-top:var(--wp--preset--spacing--80);margin-bottom:var(--wp--preset--spacing--80)\"\/>\n\n\n\n<h1 class=\"wp-block-heading\">Applied Statistics<\/h1>\n\n\n\n<div data-client-id=\"fb68dfe218c04a7a9aa8ba1012d9933f\" id=\"pdf-1\" class=\"wp-block-tropicalista-pdfembed\" style=\"height:700px\" data-api-key=\"\" data-file-name=\"yStudy-of-Applied-Statistics.pdf\" data-media-url=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/02\/yStudy-of-Applied-Statistics.pdf\" data-show-thumbnails=\"true\" data-default-view-mode=\"FIT_WIDTH\"><\/div>\n\n\n\n<h1 class=\"wp-block-heading\">AI-assisted Semiconductor Development   &#8230;.<\/h1>\n\n\n\n<div data-client-id=\"fb68dfe218c04a7a9aa8ba1012d9933f\" id=\"pdf-2\" class=\"wp-block-tropicalista-pdfembed\" style=\"height:700px\" data-api-key=\"\" data-file-name=\"yStudy-of-AI-powered-Semiconductor-Development-2026.pdf\" data-media-url=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/01\/yStudy-of-AI-powered-Semiconductor-Development-2026.pdf\" data-show-thumbnails=\"true\" data-default-view-mode=\"FIT_WIDTH\"><\/div>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" style=\"margin-top:var(--wp--preset--spacing--80);margin-bottom:var(--wp--preset--spacing--80)\"\/>\n\n\n\n<h1>Related Posts below (or view <a href=\"https:\/\/ykim.synology.me\/wordpress\/home\/posts\/\" style=\"color:#005A9C;text-decoration:underline\" target=\"_blank\">All Articles<\/a>)<\/h1>\n\n\n\n\n\n<p class=\"wp-block-paragraph\">Categories = &#8220;Data Science, AI-powered, Applied Statistics&#8221;<\/p>\n\n\n<p><div class=\"yrkt-custom-grid-wrapper\"><div class=\"yrkt-grid-container\"><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/optuna-metric-projection-6676\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"576\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260523-rainbow-over-the-sunset-1200x900px-768x576.jpg\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Optuna Metric Projection\" title=\"Optuna Metric Projection\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260523-rainbow-over-the-sunset-1200x900px-768x576.jpg 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260523-rainbow-over-the-sunset-1200x900px-300x225.jpg 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260523-rainbow-over-the-sunset-1200x900px-1024x768.jpg 1024w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260523-rainbow-over-the-sunset-1200x900px.jpg 1200w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a>\r\n        <style>\r\n            .yrkt-dynamic-badge-container {\r\n                position: absolute;\r\n                top: 10px;\r\n                left: 10px;\r\n                display: flex;\r\n                flex-direction: column; \/* \uc138\ub85c \ub098\uc5f4, \uac00\ub85c \ub098\uc5f4 row *\/\r\n                align-items: flex-start; \/* \ubc30\uacbd\uc0c9\uc774 \uae38\uc5b4\uc9c0\ub294 \uac83 \ubc29\uc9c0 *\/\r\n                gap: 5px;\r\n                z-index: 99;\r\n                width: auto;\r\n                pointer-events: none; \/* \ud074\ub9ad \ubc29\ud574 \uae08\uc9c0 *\/\r\n            }\r\n            .yrkt-dynamic-badge {\r\n                display: inline-block;\r\n                color: #ffffff;\r\n                padding: 4px 6px;\r\n                font-size: 11px;\r\n                font-weight: bold;\r\n                border-radius: 3px;\r\n                text-transform: uppercase;\r\n                box-shadow: 0 2px 4px rgba(0,0,0,0.2);\r\n                line-height: 1.2;\r\n                white-space: nowrap;\r\n            }\r\n        <\/style><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-374 { color: #0066FF !important; transition: color 0.2s; }\r\n                        .cat-color-374:hover { color: #00CCFF !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/label-engineering-slug\/\" class=\"yrkt-cat-link cat-color-374\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Label Engineering <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-377 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-377:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/hyperparameter-slug\/\" class=\"yrkt-cat-link cat-color-377\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Hyperparameter <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-375 { color: #009900 !important; transition: color 0.2s; }\r\n                        .cat-color-375:hover { color: #00CC00 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/tree-based-model-slug\/\" class=\"yrkt-cat-link cat-color-375\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Tree Based Model <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/optuna-metric-projection-6676\/\">Optuna Metric Projection<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.27<\/span> | <span>Modified: 2026.05.27<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">\u2003A concise report on projecting Optuna&#8217;s best-so-far trajectory with four saturation curves. The method estimates the expected best metric after $K$ additional trials (forward) or the trials needed to reach&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/optuna-metric-projection-6676\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/wafer-level-zernike-polynomials-6660\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"512\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/zernike_pyramid-1200x800px-768x512.png\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Wafer Level Zernike Polynomials\" title=\"Wafer Level Zernike Polynomials\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/zernike_pyramid-1200x800px-768x512.png 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/zernike_pyramid-1200x800px-300x200.png 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/zernike_pyramid-1200x800px-1024x683.png 1024w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/zernike_pyramid-1200x800px.png 1200w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-373 { color: #0033FF !important; transition: color 0.2s; }\r\n                        .cat-color-373:hover { color: #0099FF !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/feature-engineering-slug\/\" class=\"yrkt-cat-link cat-color-373\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Feature Engineering <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-374 { color: #0066FF !important; transition: color 0.2s; }\r\n                        .cat-color-374:hover { color: #00CCFF !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/label-engineering-slug\/\" class=\"yrkt-cat-link cat-color-374\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Label Engineering <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/wafer-level-zernike-polynomials-6660\/\">Wafer Level Zernike Polynomials<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.12<\/span> | <span>Modified: 2026.05.16<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">wlzpoly is a Python package that decomposes N-point wafer thickness measurements into M Zernike polynomial coefficients using LSQ or Ridge regression with LOOCV-tuned regularization. It ships with a reproducible three-stage&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/wafer-level-zernike-polynomials-6660\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/a-taxonomy-of-manufacturing-big-data-integrating-machine-and-human-data-6644\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"576\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20251226-Slope-map-trail-map-of-Ski-Santa-Fe-768x576.jpg\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"A Taxonomy of Manufacturing Big Data: Integrating Machine and Human Data\" title=\"A Taxonomy of Manufacturing Big Data: Integrating Machine and Human Data\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20251226-Slope-map-trail-map-of-Ski-Santa-Fe-768x576.jpg 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20251226-Slope-map-trail-map-of-Ski-Santa-Fe-300x225.jpg 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20251226-Slope-map-trail-map-of-Ski-Santa-Fe-1024x768.jpg 1024w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20251226-Slope-map-trail-map-of-Ski-Santa-Fe-1536x1152.jpg 1536w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20251226-Slope-map-trail-map-of-Ski-Santa-Fe.jpg 2000w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-376 { color: #F54927 !important; transition: color 0.2s; }\r\n                        .cat-color-376:hover { color: #F59527 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/pipeline-slug\/\" class=\"yrkt-cat-link cat-color-376\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Pipeline <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/a-taxonomy-of-manufacturing-big-data-integrating-machine-and-human-data-6644\/\">A Taxonomy of Manufacturing Big Data: Integrating Machine and Human Data<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.09<\/span> | <span>Modified: 2026.05.10<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">1. Introduction: The Missing Link in Smart Manufacturing \u2003Investment in smart manufacturing and big data analytics has expanded rapidly, yet the focus has remained almost exclusively on Machine Data\u2014the data&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/a-taxonomy-of-manufacturing-big-data-integrating-machine-and-human-data-6644\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/python-ml-pipeline-reproducibility-field-notes-6637\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"576\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Lowes-DO-IT-RIGHT-1000x750px-768x576.jpg\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Python ML Pipeline Reproducibility \u2014 Field Notes\" title=\"Python ML Pipeline Reproducibility \u2014 Field Notes\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Lowes-DO-IT-RIGHT-1000x750px-768x576.jpg 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Lowes-DO-IT-RIGHT-1000x750px-300x225.jpg 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Lowes-DO-IT-RIGHT-1000x750px.jpg 1000w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-376 { color: #F54927 !important; transition: color 0.2s; }\r\n                        .cat-color-376:hover { color: #F59527 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/pipeline-slug\/\" class=\"yrkt-cat-link cat-color-376\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Pipeline <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/python-ml-pipeline-reproducibility-field-notes-6637\/\">Python ML Pipeline Reproducibility \u2014 Field Notes<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.08<\/span> | <span>Modified: 2026.05.08<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">Introduction \u2003This document classifies reproducibility problems in Python Machine Learning (ML) pipelines into three chapters, plus a fourth chapter on diagnostic techniques: \u2003This classification aligns well with the Six Sigma&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/python-ml-pipeline-reproducibility-field-notes-6637\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/an-introductory-survey-on-polynomial-machine-learning-taxonomic-axes-and-hierarchical-levels-6615\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"576\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Whataburger-Austin-800x600px-768x576.jpg\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"An Introductory Survey on Polynomial Machine Learning: Taxonomic Axes and Hierarchical Levels\" title=\"An Introductory Survey on Polynomial Machine Learning: Taxonomic Axes and Hierarchical Levels\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Whataburger-Austin-800x600px-768x576.jpg 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Whataburger-Austin-800x600px-300x225.jpg 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Whataburger-Austin-800x600px.jpg 800w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-4 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-4:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/semiconductor-slug\/\" class=\"yrkt-cat-link cat-color-4\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Semiconductor <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-18 { color: #FF6347 !important; transition: color 0.2s; }\r\n                        .cat-color-18:hover { color: #FF0000 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/semiconductor-slug\/ai-powered-slug\/\" class=\"yrkt-cat-link cat-color-18\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        AI-powered <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-374 { color: #0066FF !important; transition: color 0.2s; }\r\n                        .cat-color-374:hover { color: #00CCFF !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/label-engineering-slug\/\" class=\"yrkt-cat-link cat-color-374\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Label Engineering <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/an-introductory-survey-on-polynomial-machine-learning-taxonomic-axes-and-hierarchical-levels-6615\/\">An Introductory Survey on Polynomial Machine Learning: Taxonomic Axes and Hierarchical Levels<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.06<\/span> | <span>Modified: 2026.05.06<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">\u2003This report surveys Polynomial Machine Learning (PML) at an introductory level. PML refers to the family of techniques that exploit higher-order and interaction terms of input variables to learn nonlinear&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/an-introductory-survey-on-polynomial-machine-learning-taxonomic-axes-and-hierarchical-levels-6615\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/modeling-thickness-variation-in-semiconductor-thin-film-processes-a-spatial-decomposition-approach-to-machine-learning-ml-6564\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"768\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Zernike-polynomials-9-orders-800px-768x768.png\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Modeling Thickness Variation in Semiconductor Thin-Film Processes \u2014 A Spatial Decomposition Approach to Machine Learning (ML)\" title=\"Modeling Thickness Variation in Semiconductor Thin-Film Processes \u2014 A Spatial Decomposition Approach to Machine Learning (ML)\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Zernike-polynomials-9-orders-800px-768x768.png 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Zernike-polynomials-9-orders-800px-300x300.png 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Zernike-polynomials-9-orders-800px-150x150.png 150w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/Zernike-polynomials-9-orders-800px.png 800w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-18 { color: #FF6347 !important; transition: color 0.2s; }\r\n                        .cat-color-18:hover { color: #FF0000 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/semiconductor-slug\/ai-powered-slug\/\" class=\"yrkt-cat-link cat-color-18\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        AI-powered <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-374 { color: #0066FF !important; transition: color 0.2s; }\r\n                        .cat-color-374:hover { color: #00CCFF !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/label-engineering-slug\/\" class=\"yrkt-cat-link cat-color-374\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Label Engineering <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-4 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-4:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/semiconductor-slug\/\" class=\"yrkt-cat-link cat-color-4\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Semiconductor <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-375 { color: #009900 !important; transition: color 0.2s; }\r\n                        .cat-color-375:hover { color: #00CC00 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/tree-based-model-slug\/\" class=\"yrkt-cat-link cat-color-375\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Tree Based Model <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/modeling-thickness-variation-in-semiconductor-thin-film-processes-a-spatial-decomposition-approach-to-machine-learning-ml-6564\/\">Modeling Thickness Variation in Semiconductor Thin-Film Processes \u2014 A Spatial Decomposition Approach to Machine Learning (ML)<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.04<\/span> | <span>Modified: 2026.05.06<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">\u2003Thickness uniformity in thin-film deposition determines downstream yield and device performance. Variation arises along two distinct axes \u2014 within a single wafer (Within-Wafer, WiW) and across wafers over time (Wafer-to-Wafer,&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/modeling-thickness-variation-in-semiconductor-thin-film-processes-a-spatial-decomposition-approach-to-machine-learning-ml-6564\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/are-missing-path-samples-in-tree-based-models-ood-6561\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"512\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/2025122x-Endless-Blue-Sky-Santa-Fe-Highway-900x600px-768x512.jpg\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Are Missing-Path Samples in Tree-Based Models OOD?\" title=\"Are Missing-Path Samples in Tree-Based Models OOD?\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/2025122x-Endless-Blue-Sky-Santa-Fe-Highway-900x600px-768x512.jpg 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/2025122x-Endless-Blue-Sky-Santa-Fe-Highway-900x600px-300x200.jpg 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/2025122x-Endless-Blue-Sky-Santa-Fe-Highway-900x600px.jpg 900w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/are-missing-path-samples-in-tree-based-models-ood-6561\/\">Are Missing-Path Samples in Tree-Based Models OOD?<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.03<\/span> | <span>Modified: 2026.05.04<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">Bottom Line Strictly speaking, no \u2014 but in practice, treat them as Out-of-Distribution (OOD). Missing-path samples in tree-based boosting models such as LightGBM, CatBoost, and XGBoost do not match the&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/are-missing-path-samples-in-tree-based-models-ood-6561\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/a-taxonomy-of-ml-model-failures-in-the-training-testing-gap-6548\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"576\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/03\/Irregular-Stone-Wall-Texture-800x600px-768x576.jpg\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"A Taxonomy of ML Model Failures in the Training-Testing Gap\" title=\"A Taxonomy of ML Model Failures in the Training-Testing Gap\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/03\/Irregular-Stone-Wall-Texture-800x600px-768x576.jpg 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/03\/Irregular-Stone-Wall-Texture-800x600px-300x225.jpg 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/03\/Irregular-Stone-Wall-Texture-800x600px.jpg 800w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/a-taxonomy-of-ml-model-failures-in-the-training-testing-gap-6548\/\">A Taxonomy of ML Model Failures in the Training-Testing Gap<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.03<\/span> | <span>Modified: 2026.05.03<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">Machine learning (ML) models are designed under the assumption that the training distribution P_train equals the deployment distribution P_test. In reality, this assumption breaks frequently, causing sharp accuracy drops in&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/a-taxonomy-of-ml-model-failures-in-the-training-testing-gap-6548\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/why-raw-vectorization-is-the-right-choice-for-ultra-short-time-series-t-%e2%89%a4-10-6495\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"576\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260502-Round-Rock-Tx-Spherical-Water-Tower-800x600px-768x576.jpg\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Why Raw Vectorization Is the Right Choice for Ultra-Short Time Series (T \u2264 10)\" title=\"Why Raw Vectorization Is the Right Choice for Ultra-Short Time Series (T \u2264 10)\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260502-Round-Rock-Tx-Spherical-Water-Tower-800x600px-768x576.jpg 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260502-Round-Rock-Tx-Spherical-Water-Tower-800x600px-300x225.jpg 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/05\/20260502-Round-Rock-Tx-Spherical-Water-Tower-800x600px.jpg 800w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-373 { color: #0033FF !important; transition: color 0.2s; }\r\n                        .cat-color-373:hover { color: #0099FF !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/feature-engineering-slug\/\" class=\"yrkt-cat-link cat-color-373\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Feature Engineering <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-370 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-370:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/time-series-slug\/\" class=\"yrkt-cat-link cat-color-370\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Time Series <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/why-raw-vectorization-is-the-right-choice-for-ultra-short-time-series-t-%e2%89%a4-10-6495\/\">Why Raw Vectorization Is the Right Choice for Ultra-Short Time Series (T \u2264 10)<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.05.02<\/span> | <span>Modified: 2026.05.02<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">This report analyzes why standard vectorization methods \u2014 statistical summary (mean\/var\/AUC), automatic feature extraction (tsfresh, catch22), convolutional representations (MiniRocket), and self-supervised embeddings (TS2Vec) \u2014 fail when the time series length&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/why-raw-vectorization-is-the-right-choice-for-ultra-short-time-series-t-%e2%89%a4-10-6495\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/missing-direction-learning-and-unknown-category-inference-in-gradient-boosting-libraries-6483\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"576\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Texas-Flag-Over-Margaret-Hunt-Hill-Bridge-800x600px-768x576.png\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Missing Values and Unknown Categories in Gradient Boosting Libraries\" title=\"Missing Values and Unknown Categories in Gradient Boosting Libraries\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Texas-Flag-Over-Margaret-Hunt-Hill-Bridge-800x600px-768x576.png 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Texas-Flag-Over-Margaret-Hunt-Hill-Bridge-800x600px-300x225.png 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Texas-Flag-Over-Margaret-Hunt-Hill-Bridge-800x600px.png 800w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/missing-direction-learning-and-unknown-category-inference-in-gradient-boosting-libraries-6483\/\">Missing Values and Unknown Categories in Gradient Boosting Libraries<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.04.29<\/span> | <span>Modified: 2026.04.29<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">1. Introduction This article summarizes how three popular gradient boosting libraries \u2014 LightGBM (Light Gradient Boosting Machine), XGBoost (Extreme Gradient Boosting), and CatBoost (Categorical Boosting) \u2014 handle missing values and&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/missing-direction-learning-and-unknown-category-inference-in-gradient-boosting-libraries-6483\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/noise-induced-instability-in-tree-based-feature-selection-root-causes-and-robust-countermeasures-6460\/\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"576\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Backlit-Tree-Skeleton-at-Sunset-800x600px-768x576.png\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Noise-Induced Instability in Tree-based Feature Selection: Root Causes and Robust Countermeasures\" title=\"Noise-Induced Instability in Tree-based Feature Selection: Root Causes and Robust Countermeasures\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Backlit-Tree-Skeleton-at-Sunset-800x600px-768x576.png 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Backlit-Tree-Skeleton-at-Sunset-800x600px-300x225.png 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Backlit-Tree-Skeleton-at-Sunset-800x600px.png 800w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/noise-induced-instability-in-tree-based-feature-selection-root-causes-and-robust-countermeasures-6460\/\">Noise-Induced Instability in Tree-based Feature Selection: Root Causes and Robust Countermeasures<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.04.29<\/span> | <span>Modified: 2026.04.29<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">When performing feature selection with tree-based models such as LightGBM (LGBM) or CatBoost, adding noise features to the existing set often causes truly important primary features to drop out of&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/noise-induced-instability-in-tree-based-feature-selection-root-causes-and-robust-countermeasures-6460\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><article class=\"yrkt-card\"><div class=\"yrkt-card-image\" style=\"position: relative;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/centered-r%c2%b2-vs-uncentered-r%c2%b2-6438\/\"><img loading=\"lazy\" decoding=\"async\" width=\"765\" height=\"574\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Bondi-Icebergs-pool-765x574px.png\" class=\"attachment-medium_large size-medium_large wp-post-image\" alt=\"Centered R\u00b2 vs Uncentered R\u00b2\" title=\"Centered R\u00b2 vs Uncentered R\u00b2\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Bondi-Icebergs-pool-765x574px.png 765w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Bondi-Icebergs-pool-765x574px-300x225.png 300w\" sizes=\"auto, (max-width: 765px) 100vw, 765px\" \/><\/a><\/div><div class=\"yrkt-card-content\"><div class=\"yrkt-cat-wrapper\" style=\"margin-bottom: 10px; line-height: 1;\">\r\n                        <style>\r\n                        .cat-color-56 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-56:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/\" class=\"yrkt-cat-link cat-color-56\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Data Science <\/a><span style=\"color:#ddd;\">|<\/span>\r\n                        <style>\r\n                        .cat-color-369 { color: #2b6cb0 !important; transition: color 0.2s; }\r\n                        .cat-color-369:hover { color: #1a4971 !important; text-decoration: underline !important; }\r\n                        <\/style>\r\n                        <a href=\"https:\/\/ykim.synology.me\/wordpress\/category\/data-science-slug\/evalutaion-metric-slug\/\" class=\"yrkt-cat-link cat-color-369\" style=\"font-size:0.8rem; text-decoration:none; font-weight:600;\">\r\n                        Evaluation Metric <\/a><\/div><h3 class=\"yrkt-card-title\" style=\"margin-top: 0; font-size:1.5rem;\"><a href=\"https:\/\/ykim.synology.me\/wordpress\/centered-r%c2%b2-vs-uncentered-r%c2%b2-6438\/\">Centered R\u00b2 vs Uncentered R\u00b2<\/a><\/h3><div class=\"yrkt-card-meta\" style=\"font-size:0.7rem; color: #888; margin-bottom: 12px; line-height: 1.4;\"><span>By Wolf<\/span><br><span>Created: 2026.04.25<\/span> | <span>Modified: 2026.04.26<\/span><\/div><div class=\"yrkt-card-excerpt\" style=\"font-size:1.0rem; color: #555; margin-bottom: 20px; line-height: 1.6;\">Bondi Iceberg pool 1. Introduction: R\u00b2 and Its Relation to RSQ The coefficient of determination, denoted as R\u00b2 (R-squared), is one of the most widely used validation metrics in statistics&hellip;<\/div><a class=\"yrkt-card-readmore\" style=\"font-size:0.9rem; margin-top: auto; color: #2b6cb0; text-decoration: none; font-weight: 600;\" href=\"https:\/\/ykim.synology.me\/wordpress\/centered-r%c2%b2-vs-uncentered-r%c2%b2-6438\/\">Read More <span class=\"arrow\">\u2192<\/span><\/a><\/div><\/article><\/div><div class=\"yrkt-pagination\"><span aria-current=\"page\" class=\"page-numbers current\">1<\/span>\n<a class=\"page-numbers\" href=\"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages\/153\/page\/2\/\">2<\/a>\n<a class=\"page-numbers\" href=\"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages\/153\/page\/3\/\">3<\/a>\n<a class=\"page-numbers\" href=\"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages\/153\/page\/4\/\">4<\/a>\n<a class=\"next page-numbers\" href=\"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages\/153\/page\/2\/\">Next \u00bb<\/a><\/div><\/div>\r\n    <style>\r\n        .yrkt-grid-container { display: grid; grid-template-columns: repeat(4, 1fr); gap: 30px; margin-bottom: 40px; }\r\n        .yrkt-card { \r\n            background: #fff; border-radius: 9px; overflow: hidden; box-shadow: 0 4px 15px rgba(0,0,0,0.08); \r\n            transition: transform 0.3s ease; display: flex; flex-direction: column; height: 100%;\r\n\t\t\tposition: relative !important;  \/* Badge\ub97c \uc704\ud574 \ubd80\ubaa8 \uc694\uc18c\uc5d0 position relative \ucd94\uac00 *\/\r\n        }\r\n        .yrkt-card:hover {\r\n            animation: yrckt_wiggle 0.4s linear infinite !important;\r\n            transition: box-shadow 0.3s ease;\r\n            box-shadow: 0 10px 25px rgba(0,0,0,0.1) !important;\r\n        }\r\n        .yrkt-card-image img { width: 100%; height: 200px; object-fit: cover; display: block; }\r\n        .yrkt-cat-link:hover { text-decoration: underline !important; }\r\n        .yrkt-card-content { padding: 25px; flex-grow: 1; display: flex; flex-direction: column; }\r\n        .yrkt-card-title { line-height: 1.3; margin: 0 0 10px 0; font-weight: 700; }\r\n        .yrkt-card-title a { color: #222; text-decoration: none; }\r\n        .yrkt-card-title a:hover { color: #2b6cb0; text-decoration: underline; }\r\n        .yrkt-card-readmore:hover .arrow { transform: translateX(5px); display: inline-block; transition: transform 0.2s; }\r\n        \r\n        .yrkt-pagination { text-align: center; margin-top: 40px; }\r\n        .yrkt-pagination .page-numbers { padding: 8px 16px; margin: 0 5px; border: 1px solid #eee; border-radius: 50px; text-decoration: none; color: #444; }\r\n        .yrkt-pagination .page-numbers.current { background: #2b6cb0; color: #fff; border-color: #2b6cb0; }\r\n        \r\n        @media (max-width: 992px) { .yrkt-grid-container { grid-template-columns: repeat(2, 1fr); } }\r\n        @media (max-width: 650px) { .yrkt-grid-container { grid-template-columns: 1fr; } }\r\n    <\/style>\r\n    <script>\r\n    (function() {\r\n        document.addEventListener(\"mouseover\", function(e) {\r\n            const card = e.target.closest(\".yrkt-card\");\r\n            if (card) {\r\n                card.style.setProperty(\"animation\", \"yrckt_wiggle 0.3s linear infinite\", \"important\");\r\n            }\r\n        });\r\n        document.addEventListener(\"mouseout\", function(e) {\r\n            const card = e.target.closest(\".yrkt-card\");\r\n            if (card) {\r\n                card.style.animation = \"none\";\r\n            }\r\n        });\r\n    })();\r\n    <\/script><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<div style='text-align:center' class='yasr-auto-insert-overall'><\/div><div style='text-align:center' class='yasr-auto-insert-visitor'><\/div>","protected":false},"excerpt":{"rendered":"<p>Experimental, AI\u2011assisted, data\u2011driven methodologies integrated into engineering platforms and supported by semiconductor, statistical, machine\u2011learning, and deep\u2011learning technologies to optimize semiconductor manufacturing across process, device, and yield development. The following are the key components of my work on AI\u2011Driven Engineering Platforms: The motivation for technology convergence that integrates semiconductor technology with data science is that this&#8230;<\/p>\n","protected":false},"author":1,"featured_media":5793,"parent":778,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"_kadence_starter_templates_imported_post":false,"_kad_post_transparent":"","_kad_post_title":"","_kad_post_layout":"","_kad_post_sidebar_id":"","_kad_post_content_style":"","_kad_post_vertical_padding":"","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"_kad_post_classname":"","yasr_overall_rating":0,"yasr_post_is_review":"","yasr_auto_insert_disabled":"","yasr_review_type":"","iawp_total_views":12,"footnotes":""},"class_list":["post-153","page","type-page","status-publish","has-post-thumbnail","hentry"],"yasr_visitor_votes":{"stars_attributes":{"read_only":false,"span_bottom":false},"number_of_votes":1,"sum_votes":4},"_links":{"self":[{"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages\/153","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/comments?post=153"}],"version-history":[{"count":69,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages\/153\/revisions"}],"predecessor-version":[{"id":6321,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages\/153\/revisions\/6321"}],"up":[{"embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/pages\/778"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/media\/5793"}],"wp:attachment":[{"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/media?parent=153"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}