{"id":55456,"date":"2024-04-16T00:27:42","date_gmt":"2024-04-16T00:27:42","guid":{"rendered":"https:\/\/exam.pscnotes.com\/mcq\/?p=55456"},"modified":"2024-04-16T00:27:42","modified_gmt":"2024-04-16T00:27:42","slug":"suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi","status":"publish","type":"post","link":"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/","title":{"rendered":"Suppose we train a hard-margin linear SVM on n > 100 data points in R2, yielding a hyperplane with exactly 2 support vectors. If we add one more data point and retrain the classifier, what is the maximum possible number of support vectors for the new hyperplane (assuming the n + 1 points are linearly separable)?"},"content":{"rendered":"<p>\r\n    <!-- Check if it's an AMP page -->\r\n            <!-- Non-AMP version -->\r\n        <div class=\"mcq-container\" data-quiz-id=\"quizState_6a9832c0c2a79\">\r\n                                            <div class=\"option\" data-option-key=\"option1\" data-is-correct=\"true\">\r\n                    2                <\/div>\r\n                                            <div class=\"option\" data-option-key=\"option2\" data-is-correct=\"false\">\r\n                    3                <\/div>\r\n                                            <div class=\"option\" data-option-key=\"option3\" data-is-correct=\"false\">\r\n                    n                <\/div>\r\n                                            <div class=\"option\" data-option-key=\"option4\" data-is-correct=\"false\">\r\n                    n+1                <\/div>\r\n                            \r\n            <!-- Feedback messages for non-AMP -->\r\n            <div class=\"feedback\" data-feedback=\"wrong\">Answer is Right!<\/div>\r\n            <div class=\"feedback\" data-feedback=\"right\">Answer is Wrong!<\/div>\r\n        <\/div>\r\n\r\n        <script>\r\n        document.addEventListener('DOMContentLoaded', function () {\r\n            var containers = document.querySelectorAll('.mcq-container');\r\n\r\n            containers.forEach(function(container) {\r\n                var options = container.querySelectorAll('.option');\r\n                var feedbackSelect = container.querySelector('[data-feedback=\"select\"]');\r\n                var feedbackWrong = container.querySelector('[data-feedback=\"wrong\"]');\r\n                var feedbackRight = container.querySelector('[data-feedback=\"right\"]');\r\n\r\n                options.forEach(function(option) {\r\n                    option.addEventListener('click', function() {\r\n                        var selectedOption = option.getAttribute('data-option-key');\r\n                        var isCorrect = option.getAttribute('data-is-correct') === 'true';\r\n\r\n                        \/\/ Remove previous selections\r\n                        options.forEach(function(opt) {\r\n                            opt.classList.remove('correct', 'incorrect');\r\n                        });\r\n\r\n                        \/\/ Add the correct\/incorrect class\r\n                        if (isCorrect) {\r\n                            option.classList.add('correct');\r\n                            feedbackRight.hidden = false;\r\n                            feedbackWrong.hidden = true;\r\n                        } else {\r\n                            option.classList.add('incorrect');\r\n                            feedbackRight.hidden = true;\r\n                            feedbackWrong.hidden = false;\r\n                        }\r\n\r\n                        \/\/ Hide select feedback\r\n                        feedbackSelect.hidden = true;\r\n                    });\r\n                });\r\n            });\r\n        });\r\n        <\/script>\r\n    \r\n    <!--more--><\/p>\n<p>The correct answer is $\\boxed{\\text{B}}$.<\/p>\n<p>A support vector is a data point that lies on the decision boundary of a support vector machine (SVM). The decision boundary is the hyperplane that separates the data points into two classes.<\/p>\n<p>In a hard-margin SVM, the decision boundary is chosen to maximize the margin, which is the distance between the decision boundary and the nearest data points. This means that the support vectors are the data points that are closest to the decision boundary.<\/p>\n<p>If we add one more data point <div class=\"youtube-subscribe-container\">\r\n        <a href=\"https:\/\/www.youtube.com\/channel\/UCNHT8lW-JmLC68rjBfZhdkg?sub_confirmation=1\" target=\"_blank\" class=\"youtube-subscribe-button\">\r\n            <span class=\"youtube-icon\">\r\n                <svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" viewBox=\"0 0 576 512\">\r\n                    <path d=\"M549.7 124.1c-6.3-23.7-24.8-42.3-48.3-48.6C458.8 64 288 64 288 64S117.2 64 74.6 75.5c-23.5 6.3-42 24.9-48.3 48.6-11.4 42.9-11.4 132.3-11.4 132.3s0 89.4 11.4 132.3c6.3 23.7 24.8 41.5 48.3 47.8C117.2 448 288 448 288 448s170.8 0 213.4-11.5c23.5-6.3 42-24.2 48.3-47.8 11.4-42.9 11.4-132.3 11.4-132.3s0-89.4-11.4-132.3zm-317.5 213.5V175.2l142.7 81.2-142.7 81.2z\"\/>\r\n                <\/svg>\r\n            <\/span>\r\n            Subscribe on YouTube\r\n        <\/a>\r\n    <\/div> to the dataset, the decision boundary may change. If the new data <div class=\"telegram-channel-container\">\r\n        <a href=\"https:\/\/t.me\/pscnotes2025\" target=\"_blank\" class=\"telegram-channel-button\">\r\n            <span class=\"telegram-icon\">\r\n                <svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" viewBox=\"0 0 496 512\">\r\n                    <path fill=\"white\" d=\"M248,8C111,8,0,119,0,256s111,248,248,248s248-111,248-248S385,8,248,8z M362,177L320,367c-3,14-10,18-20,14l-56-41l-27,26 c-3,3-5,5-10,5l4-63L323,196c5-5-1-7-8-3l-98,62l-42-13c-9-3-10-9,2-14l162-63C351,160,365,164,362,177z\"\/>\r\n                <\/svg>\r\n            <\/span>\r\n            Join Our Telegram Channel\r\n        <\/a>\r\n    <\/div> point is on the same side of the decision boundary as the two support vectors, then the number of support vectors will remain at 2. However, if the new data point is on the opposite side of the decision boundary, then it will become a support vector, and the number of support vectors will increase to 3.<\/p>\n<p>In general, the maximum possible number of support vectors for a dataset with $n$ data points is $n$. However, this is only possible if the data points are linearly separable. If the data points are not linearly separable, then there will always be some data points that are on the wrong side of the decision boundary, and these data points will be support vectors.<\/p>\n<p>In the case of the question, we are told that the original dataset has $n&gt;100$ data points and that the hyperplane has exactly 2 support vectors. This means that the data points are linearly separable. If we add one more data point to the dataset, the maximum possible number of support vectors for the new hyperplane is 3.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Join Our Telegram Channel Subscribe on YouTube<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[729],"tags":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v22.2 (Yoast SEO v23.3) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Suppose we train a hard-margin linear SVM on n &gt; 100 data points in R2, yielding a hyperplane with exactly 2 support vectors. If we add one more data point and retrain the classifier, what is the maximum possible number of support vectors for the new hyperplane (assuming the n + 1 points are linearly separable)?<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Suppose we train a hard-margin linear SVM on n &gt; 100 data points in R2, yielding a hyperplane with exactly 2 support vectors. If we add one more data point and retrain the classifier, what is the maximum possible number of support vectors for the new hyperplane (assuming the n + 1 points are linearly separable)?\" \/>\n<meta property=\"og:description\" content=\"Subscribe on YouTube\" \/>\n<meta property=\"og:url\" content=\"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/\" \/>\n<meta property=\"og:site_name\" content=\"MCQ and Quiz for Exams\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-16T00:27:42+00:00\" \/>\n<meta name=\"author\" content=\"rawan239\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"rawan239\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Suppose we train a hard-margin linear SVM on n > 100 data points in R2, yielding a hyperplane with exactly 2 support vectors. If we add one more data point and retrain the classifier, what is the maximum possible number of support vectors for the new hyperplane (assuming the n + 1 points are linearly separable)?","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/","og_locale":"en_US","og_type":"article","og_title":"Suppose we train a hard-margin linear SVM on n > 100 data points in R2, yielding a hyperplane with exactly 2 support vectors. If we add one more data point and retrain the classifier, what is the maximum possible number of support vectors for the new hyperplane (assuming the n + 1 points are linearly separable)?","og_description":"Subscribe on YouTube","og_url":"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/","og_site_name":"MCQ and Quiz for Exams","article_published_time":"2024-04-16T00:27:42+00:00","author":"rawan239","twitter_card":"summary_large_image","twitter_misc":{"Written by":"rawan239","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/","url":"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/","name":"Suppose we train a hard-margin linear SVM on n > 100 data points in R2, yielding a hyperplane with exactly 2 support vectors. If we add one more data point and retrain the classifier, what is the maximum possible number of support vectors for the new hyperplane (assuming the n + 1 points are linearly separable)?","isPartOf":{"@id":"https:\/\/exam.pscnotes.com\/mcq\/#website"},"datePublished":"2024-04-16T00:27:42+00:00","dateModified":"2024-04-16T00:27:42+00:00","author":{"@id":"https:\/\/exam.pscnotes.com\/mcq\/#\/schema\/person\/5807dafeb27d2ec82344d6cbd6c3d209"},"breadcrumb":{"@id":"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/exam.pscnotes.com\/mcq\/suppose-we-train-a-hard-margin-linear-svm-on-n-100-data-points-in-r2-yielding-a-hyperplane-with-exactly-2-support-vectors-if-we-add-one-more-data-point-and-retrain-the-classifier-what-is-the-maxi\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/exam.pscnotes.com\/mcq\/"},{"@type":"ListItem","position":2,"name":"mcq","item":"https:\/\/exam.pscnotes.com\/mcq\/category\/mcq\/"},{"@type":"ListItem","position":3,"name":"Machine learning","item":"https:\/\/exam.pscnotes.com\/mcq\/category\/mcq\/machine-learning\/"},{"@type":"ListItem","position":4,"name":"Suppose we train a hard-margin linear SVM on n > 100 data points in R2, yielding a hyperplane with exactly 2 support vectors. If we add one more data point and retrain the classifier, what is the maximum possible number of support vectors for the new hyperplane (assuming the n + 1 points are linearly separable)?"}]},{"@type":"WebSite","@id":"https:\/\/exam.pscnotes.com\/mcq\/#website","url":"https:\/\/exam.pscnotes.com\/mcq\/","name":"MCQ and Quiz for Exams","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/exam.pscnotes.com\/mcq\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/exam.pscnotes.com\/mcq\/#\/schema\/person\/5807dafeb27d2ec82344d6cbd6c3d209","name":"rawan239","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/exam.pscnotes.com\/mcq\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/d97f17072bfa490596c8f78363955d55?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/d97f17072bfa490596c8f78363955d55?s=96&d=mm&r=g","caption":"rawan239"},"sameAs":["https:\/\/exam.pscnotes.com"],"url":"https:\/\/exam.pscnotes.com\/mcq\/author\/rawan239\/"}]}},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/posts\/55456"}],"collection":[{"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/comments?post=55456"}],"version-history":[{"count":0,"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/posts\/55456\/revisions"}],"wp:attachment":[{"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/media?parent=55456"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/categories?post=55456"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/exam.pscnotes.com\/mcq\/wp-json\/wp\/v2\/tags?post=55456"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}