[{"data":1,"prerenderedAt":785},["ShallowReactive",2],{"navigation_docs":3,"-machine-learning-train-validation-test-dataset":352,"-machine-learning-train-validation-test-dataset-surround":780},[4,54,83,116,125,161,179,200],{"title":5,"path":6,"stem":7,"children":8},"Ai","/ai","ai",[9,12,42,46,50],{"title":10,"path":6,"stem":11},"AI 技術探索","ai/index",{"title":13,"path":14,"stem":15,"children":16,"page":41},"Rag","/ai/rag","ai/RAG",[17,21,25,29,33,37],{"title":18,"path":19,"stem":20},"BM25 演算法深入解析：從 TF-IDF 到現代搜尋引擎的核心技術","/ai/rag/bm25-deep-dive-from-tf-idf-to-rag","ai/RAG/bm25-deep-dive-from-tf-idf-to-rag",{"title":22,"path":23,"stem":24},"Dense Retrieval（向量檢索）深入解析","/ai/rag/dense-retrieval-deep-dive","ai/RAG/dense-retrieval-deep-dive",{"title":26,"path":27,"stem":28},"RAG（Retrieval-Augmented Generation）原理與實作入門","/ai/rag/rag-intro-principles-and-implementation","ai/RAG/rag-intro-principles-and-implementation",{"title":30,"path":31,"stem":32},"RAG Retrieval Strategy 深入解析","/ai/rag/rag-retrieval-strategy-deep-dive","ai/RAG/rag-retrieval-strategy-deep-dive",{"title":34,"path":35,"stem":36},"Reciprocal Rank Fusion（RRF）教學：打造更穩定的檢索融合策略","/ai/rag/rrf-reciprocal-rank-fusion-guide","ai/RAG/rrf-reciprocal-rank-fusion-guide",{"title":38,"path":39,"stem":40},"TF-IDF（Term Frequency–Inverse Document Frequency）深入解析","/ai/rag/tf-idf-deep-dive","ai/RAG/tf-idf-deep-dive",false,{"title":43,"path":44,"stem":45},"Docus AI 功能完整實作指南","/ai/docus-ai-implementation","ai/docus-ai-implementation",{"title":47,"path":48,"stem":49},"llms.txt 是什麼？在 Nuxt 中控制 AI 與搜尋引擎爬蟲的新方式","/ai/llms-txt","ai/llms-txt",{"title":51,"path":52,"stem":53},"MCP（Model Context Protocol）是什麼？用「AI 的 USB-C」理解模型如何安全連接工具與資料","/ai/mcp_concept","ai/mcp_concept",{"title":55,"path":56,"stem":57,"children":58,"page":41},"Data Analysis","/data-analysis","data-analysis",[59,63,67,71,75,79],{"title":60,"path":61,"stem":62},"Exploratory Data Analysis（EDA）資料探索分析入門","/data-analysis/exploratory-data-analysis-eda","data-analysis/exploratory-data-analysis-eda",{"title":64,"path":65,"stem":66},"PR-AUC 深入解析：不平衡分類問題的重要評估指標","/data-analysis/pr-auc-for-imbalanced-classification","data-analysis/pr-auc-for-imbalanced-classification",{"title":68,"path":69,"stem":70},"ROC-AUC 深入解析：理解分類模型的判斷能力","/data-analysis/roc-auc-complete-guide","data-analysis/roc-auc-complete-guide",{"title":72,"path":73,"stem":74},"SHAP（SHapley Additive exPlanations）模型解釋方法深入解析","/data-analysis/shap-model-interpretation-complete-guide","data-analysis/shap-model-interpretation-complete-guide",{"title":76,"path":77,"stem":78},"Social Network Analysis（SNA）深入解析","/data-analysis/social-network-analysis-sna","data-analysis/social-network-analysis-sna",{"title":80,"path":81,"stem":82},"Time-based Split：為什麼時間序列資料不能使用 Random Split？","/data-analysis/time-based-split-vs-random-split","data-analysis/time-based-split-vs-random-split",{"title":84,"path":85,"stem":86,"children":87,"page":41},"MachineLearning","/machine_learning","machine_learning",[88,92,96,100,104,108,112],{"title":89,"path":90,"stem":91},"Confusion Matrix（混淆矩陣）完整解析","/machine_learning/confusion-matrix","machine_learning/confusion-matrix",{"title":93,"path":94,"stem":95},"Decision Tree 模型完整教學：從原理到 Python 實作","/machine_learning/decision-tree-complete-guide","machine_learning/decision-tree-complete-guide",{"title":97,"path":98,"stem":99},"為什麼 Decision Tree 在 Tabular Data 上常常勝過 Deep Learning？","/machine_learning/decision-tree-vs-deep-learning-on-tabular-data","machine_learning/decision-tree-vs-deep-learning-on-tabular-data",{"title":101,"path":102,"stem":103},"LightGBM 模型入門：理解高效能的 Gradient Boosting 演算法","/machine_learning/lightgbm-intro-for-tabular-data","machine_learning/lightgbm-intro-for-tabular-data",{"title":105,"path":106,"stem":107},"Logistic Regression（Logit 回歸）完整教學","/machine_learning/logistic-regression-complete-guide","machine_learning/logistic-regression-complete-guide",{"title":109,"path":110,"stem":111},"為什麼模型訓練需要 Train / Validation / Test Dataset？","/machine_learning/train-validation-test-dataset","machine_learning/train-validation-test-dataset",{"title":113,"path":114,"stem":115},"XGBoost 原理與實務教學","/machine_learning/xgboost-complete-guide","machine_learning/xgboost-complete-guide",{"title":117,"path":118,"stem":119,"children":120,"page":41},"Network","/network","network",[121],{"title":122,"path":123,"stem":124},"DNS 設定入門：CNAME vs A Record 完整解析","/network/dns-cname-vs-a-record-guide","network/dns-cname-vs-a-record-guide",{"title":126,"path":127,"stem":128,"children":129},"Nuxt","/nuxt","nuxt",[130,133,137,141,145,149,153,157],{"title":131,"path":127,"stem":132},"Nuxt 實戰指南","nuxt/index",{"title":134,"path":135,"stem":136},"Abstraction Layer 與 Adapter 的差別，一次搞懂設計角色","/nuxt/adapter_abstraction_layer","nuxt/adapter_abstraction_layer",{"title":138,"path":139,"stem":140},"Nuxt 4 全面理解 — 專案檔案結構解析","/nuxt/directory_structure","nuxt/directory_structure",{"title":142,"path":143,"stem":144},"Nuxt 前端 build 流程完整解析","/nuxt/frontend_build","nuxt/frontend_build",{"title":146,"path":147,"stem":148},"Nitro 是什麼？從 Nuxt 專案到 Server 與 Edge 的關鍵引擎","/nuxt/nitro","nuxt/nitro",{"title":150,"path":151,"stem":152},"深入理解 Nuxt 的 .nuxt 與 .output：為什麼部署時一定要分清楚？","/nuxt/nuxt_and_output","nuxt/nuxt_and_output",{"title":154,"path":155,"stem":156},"Nuxt 中 dev、build、preview 的差異一次搞懂","/nuxt/nuxt_dev_build_preview","nuxt/nuxt_dev_build_preview",{"title":158,"path":159,"stem":160},"Nuxt Image vs \u003Cimg>：為什麼 Nuxt 3 專案幾乎都該用 \u003CNuxtImg>？","/nuxt/nuxt_image","nuxt/nuxt_image",{"title":162,"path":163,"stem":164,"children":165},"Python 程式開發","/python","python/index",[166,167,171,175],{"title":162,"path":163,"stem":164},{"title":168,"path":169,"stem":170},"如何在 FastAPI 中調用記憶體 Buffer 回傳圖片 (附實例)","/python/memory_buffer","python/memory_buffer",{"title":172,"path":173,"stem":174},"Python 單元測試教學：如何為你的程式撰寫 Test","/python/python-unit-testing-unittest-pytest","python/python-unit-testing-unittest-pytest",{"title":176,"path":177,"stem":178},"如何使用 uv 取代 pip：改善 Python 專案的開發流程","/python/uv","python/uv",{"title":180,"path":181,"stem":182,"children":183,"page":41},"Statistic","/statistic","statistic",[184,188,192,196],{"title":185,"path":186,"stem":187},"卡方檢定（Chi-Square Test）入門教學","/statistic/chi-square-test-intro","statistic/chi-square-test-intro",{"title":189,"path":190,"stem":191},"常見抽樣方法（Sampling Methods）教學：Stratified、Quota、Convenience、Systematic、Simple Random","/statistic/common-sampling-methods-guide","statistic/common-sampling-methods-guide",{"title":193,"path":194,"stem":195},"Cramér’s V 指標介紹：如何衡量兩個類別變數之間的關聯","/statistic/cramers-v-for-categorical-association","statistic/cramers-v-for-categorical-association",{"title":197,"path":198,"stem":199},"Mann–Whitney U 與 Kolmogorov–Smirnov（KS）檢定：非參數統計檢定的入門指南","/statistic/mann-whitney-u-and-ks-test-intro","statistic/mann-whitney-u-and-ks-test-intro",{"title":201,"path":202,"stem":203,"children":204},"WebDev","/web_dev","web_dev",[205,208,234,248,282,312,334],{"title":206,"path":202,"stem":207},"Web 前端開發","web_dev/index",{"title":209,"path":210,"stem":211,"children":212},"瀏覽器與渲染","/web_dev/browser","web_dev/browser/index",[213,214,218,222,226,230],{"title":209,"path":210,"stem":211},{"title":215,"path":216,"stem":217},"瀏覽器儲存空間完整解析：Cookie、localStorage、IndexedDB 到 Cache Storage","/web_dev/browser/browser-storage-comprehensive-guide","web_dev/browser/browser-storage-comprehensive-guide",{"title":219,"path":220,"stem":221},"DOM (Document Object Model) 深入解析","/web_dev/browser/dom","web_dev/browser/dom",{"title":223,"path":224,"stem":225},"Service Worker Request Flow 深入解析","/web_dev/browser/service-worker-request-flow","web_dev/browser/service-worker-request-flow",{"title":227,"path":228,"stem":229},"CSR、SSR 與 SSG 是什麼？前端渲染策略完整比較","/web_dev/browser/ssr_csr_ssg","web_dev/browser/ssr_csr_ssg",{"title":231,"path":232,"stem":233},"Virtual DOM 深入解析：為什麼它能優化前端效能？","/web_dev/browser/virtual_dom","web_dev/browser/virtual_dom",{"title":235,"path":236,"stem":237,"children":238},"圖形技術","/web_dev/graphics","web_dev/graphics/index",[239,240,244],{"title":235,"path":236,"stem":237},{"title":241,"path":242,"stem":243},"為什麼 Three.js 專案幾乎都選擇 CSR？從 SSR 問題談起","/web_dev/graphics/threejs_csr","web_dev/graphics/threejs_csr",{"title":245,"path":246,"stem":247},"WebGL 是什麼？為什麼前端 3D 幾乎都靠它？","/web_dev/graphics/webgl","web_dev/graphics/webGL",{"title":249,"path":250,"stem":251,"children":252},"架構與配置","/web_dev/infrastructure","web_dev/infrastructure/index",[253,254,258,262,266,270,274,278],{"title":249,"path":250,"stem":251},{"title":255,"path":256,"stem":257},"Zeabur + K3s + Nuxt 部署架構完整解析","/web_dev/infrastructure/k3s-zeabur","web_dev/infrastructure/K3s-zeabur",{"title":259,"path":260,"stem":261},"ECS vs Docker vs Kubernetes：從部署堆疊理解三層架構","/web_dev/infrastructure/ecs-docker-kubernetes-stack","web_dev/infrastructure/ecs-docker-kubernetes-stack",{"title":263,"path":264,"stem":265},"ECS vs VPS 是什麼？從部署網站的角度一次搞懂差別","/web_dev/infrastructure/ecs-vs-vps","web_dev/infrastructure/ecs-vs-vps",{"title":267,"path":268,"stem":269},"Zeabur 內網服務連線完整入門指南","/web_dev/infrastructure/k3s-internal-networking","web_dev/infrastructure/k3s-internal-networking",{"title":271,"path":272,"stem":273},"使用 Microservices 架構設計系統的優勢解析","/web_dev/infrastructure/microservices-architecture-advantages","web_dev/infrastructure/microservices-architecture-advantages",{"title":275,"path":276,"stem":277},"Nginx 入門教學：從反向代理到與 Kubernetes 的架構比較","/web_dev/infrastructure/nginx-intro","web_dev/infrastructure/nginx-intro",{"title":279,"path":280,"stem":281},"YAML 配置是什麼？為什麼現代開發都在用它","/web_dev/infrastructure/yaml-configuration","web_dev/infrastructure/yaml-configuration",{"title":283,"path":284,"stem":285,"children":286},"網絡與通訊","/web_dev/network","web_dev/network/index",[287,288,292,296,300,304,308],{"title":283,"path":284,"stem":285},{"title":289,"path":290,"stem":291},"HTTP Request 結構完整解析：從 Request Line 到 Header 一次看懂","/web_dev/network/http-request-structure","web_dev/network/http-request-structure",{"title":293,"path":294,"stem":295},"OSI 模型（Open Systems Interconnection Model）完整解析","/web_dev/network/osi-model","web_dev/network/osi-model",{"title":297,"path":298,"stem":299},"RESTful API 設計原則與實務解析","/web_dev/network/restful-api","web_dev/network/restful-api",{"title":301,"path":302,"stem":303},"RESTful API 五大設計原則深入解析","/web_dev/network/restful-api-principles","web_dev/network/restful-api-principles",{"title":305,"path":306,"stem":307},"Server-Sent Events (SSE) 深入解析與實作教學","/web_dev/network/sse-introduction","web_dev/network/sse-introduction",{"title":309,"path":310,"stem":311},"WebSocket 入門教學：從概念到 Node.js 實作","/web_dev/network/websocket-introduction","web_dev/network/websocket-introduction",{"title":313,"path":314,"stem":315,"children":316},"認證與安全","/web_dev/security","web_dev/security/index",[317,318,322,326,330],{"title":313,"path":314,"stem":315},{"title":319,"path":320,"stem":321},"使用 Cookie 與 Session 建立使用者驗證（完整新手教學）","/web_dev/security/cookie-session-authentication","web_dev/security/cookie-session-authentication",{"title":323,"path":324,"stem":325},"JWT 驗證機制完整解析：從登入流程到實務應用","/web_dev/security/jwt-authentication","web_dev/security/jwt-authentication",{"title":327,"path":328,"stem":329},"Secret Key 簽名是什麼？從零理解資料簽名的本質","/web_dev/security/secret-key-signing","web_dev/security/secret-key-signing",{"title":331,"path":332,"stem":333},"SSH（Secure Shell）是什麼？從遠端登入到安全通道的核心概念","/web_dev/security/ssh","web_dev/security/ssh",{"title":335,"path":336,"stem":337,"children":338},"SEO 與規範","/web_dev/seo","web_dev/seo/index",[339,340,344,348],{"title":335,"path":336,"stem":337},{"title":341,"path":342,"stem":343},"Canonical URL 是什麼？用生活化方式搞懂前端 SEO 的基本保命符","/web_dev/seo/canonical_link","web_dev/seo/canonical_link",{"title":345,"path":346,"stem":347},"robots.txt 是什麼？SEO 的第一道守門員","/web_dev/seo/robot_txt","web_dev/seo/robot_txt",{"title":349,"path":350,"stem":351},"Nuxt SEO 中的 Meta 與 SEO 工具是如何運作的？","/web_dev/seo/seo","web_dev/seo/seo",{"id":353,"title":109,"body":354,"description":768,"extension":769,"links":770,"meta":771,"navigation":777,"path":110,"seo":778,"stem":111,"__hash__":779},"docs/machine_learning/train-validation-test-dataset.md",{"type":355,"value":356,"toc":757},"minimark",[357,362,371,374,381,384,397,400,403,407,413,416,423,476,479,486,488,492,498,501,515,521,524,527,577,584,587,589,593,599,605,608,611,625,627,663,666,668,672,675,681,684,690,693,696,707,714,716,719,722,739,742,744,747,754],[358,359,361],"h2",{"id":360},"為什麼機器學習需要將資料切分","為什麼機器學習需要將資料切分？",[363,364,365,366,370],"p",{},"在機器學習的流程中，一個常見且非常重要的步驟，就是將資料切分成 ",[367,368,369],"strong",{},"Train、Validation 與 Test 三種不同的資料集","。",[363,372,373],{},"這樣做的目的，是為了確保模型在訓練時不會「過度記住資料」，而是能真正學會資料中的規律，並在未見過的新資料上依然保持良好的表現。",[363,375,376,377,380],{},"如果所有資料都直接拿來訓練模型，模型可能會產生一個問題：",[367,378,379],{},"Overfitting（過度擬合）","。這代表模型只是在記憶訓練資料，而不是學習到可以泛化到新資料的模式。當模型遇到新的資料時，表現就會大幅下降。",[363,382,383],{},"因此，在資料科學與機器學習中，通常會將資料切分為三個不同用途的集合：",[385,386,387,391,394],"ul",{},[388,389,390],"li",{},"Train dataset",[388,392,393],{},"Validation dataset",[388,395,396],{},"Test dataset",[363,398,399],{},"這三種資料集各自扮演不同角色，共同確保模型訓練的可靠性。",[401,402],"hr",{},[358,404,406],{"id":405},"train-dataset模型學習的來源","Train Dataset：模型學習的來源",[363,408,409,412],{},[367,410,411],{},"Train dataset（訓練資料）"," 是用來讓模型真正學習資料模式的資料集。",[363,414,415],{},"在訓練過程中，模型會透過這些資料來調整內部參數。例如在一個分類問題中，模型會觀察每一筆資料的特徵（features）與對應的標籤（label），然後透過優化演算法（如 Gradient Descent）不斷更新模型參數，使預測結果越來越接近真實標籤。",[363,417,418,419,422],{},"例如在 ",[367,420,421],{},"金融詐欺偵測（Fraud Detection）"," 的問題中，Train dataset 可能包含：",[424,425,426,445],"table",{},[427,428,429],"thead",{},[430,431,432,436,439,442],"tr",{},[433,434,435],"th",{},"Transaction Amount",[433,437,438],{},"Location",[433,440,441],{},"Device",[433,443,444],{},"Label",[446,447,448,463],"tbody",{},[430,449,450,454,457,460],{},[451,452,453],"td",{},"1000",[451,455,456],{},"Taiwan",[451,458,459],{},"Mobile",[451,461,462],{},"Fraud",[430,464,465,468,470,473],{},[451,466,467],{},"50",[451,469,456],{},[451,471,472],{},"Desktop",[451,474,475],{},"Normal",[363,477,478],{},"模型會透過大量類似的資料，學習哪些特徵可能代表詐欺交易。",[363,480,481,482,485],{},"需要注意的是，",[367,483,484],{},"Train dataset 的目標是學習模型參數，而不是評估模型好壞","。如果我們只看訓練資料上的表現，模型往往會看起來非常好，但這並不代表它在真實世界中也會表現良好。",[401,487],{},[358,489,491],{"id":490},"validation-dataset模型調整與選擇","Validation Dataset：模型調整與選擇",[363,493,494,497],{},[367,495,496],{},"Validation dataset（驗證資料）"," 的主要用途是用來調整模型與選擇最佳設定。",[363,499,500],{},"在模型訓練過程中，我們通常會有許多需要決定的設定，例如：",[385,502,503,506,509,512],{},[388,504,505],{},"Tree model 的最大深度",[388,507,508],{},"Learning rate",[388,510,511],{},"Regularization strength",[388,513,514],{},"神經網路的層數與節點數",[363,516,517,518,370],{},"這些設定被稱為 ",[367,519,520],{},"hyperparameters（超參數）",[363,522,523],{},"Validation dataset 的作用，就是在不同模型設定之間進行比較，找出表現最好的組合。",[363,525,526],{},"例如：",[424,528,529,542],{},[427,530,531],{},[430,532,533,536,539],{},[433,534,535],{},"Model",[433,537,538],{},"Max Depth",[433,540,541],{},"Validation AUC",[446,543,544,555,566],{},[430,545,546,549,552],{},[451,547,548],{},"Model A",[451,550,551],{},"3",[451,553,554],{},"0.81",[430,556,557,560,563],{},[451,558,559],{},"Model B",[451,561,562],{},"6",[451,564,565],{},"0.86",[430,567,568,571,574],{},[451,569,570],{},"Model C",[451,572,573],{},"10",[451,575,576],{},"0.83",[363,578,579,580,583],{},"透過 validation dataset，我們可以選擇 ",[367,581,582],{},"Max Depth = 6"," 的模型。",[363,585,586],{},"需要注意的是，如果我們反覆根據 validation dataset 調整模型，模型其實已經「間接學習到 validation dataset」。因此 validation dataset 並不能作為最終模型表現的評估標準。",[401,588],{},[358,590,592],{"id":591},"test-dataset最終的模型評估","Test Dataset：最終的模型評估",[363,594,595,598],{},[367,596,597],{},"Test dataset（測試資料）"," 是用來做模型最終評估的資料。",[363,600,601,602,370],{},"這一組資料在整個模型開發過程中 ",[367,603,604],{},"完全不能被使用於訓練或調整模型",[363,606,607],{},"它的存在目的，是模擬模型在真實世界中遇到「從未見過的資料」時的表現。",[363,609,610],{},"當模型訓練完成並且選定最佳設定後，我們才會在 Test dataset 上進行一次評估，例如計算：",[385,612,613,616,619,622],{},[388,614,615],{},"Accuracy",[388,617,618],{},"ROC-AUC",[388,620,621],{},"PR-AUC",[388,623,624],{},"Precision / Recall",[363,626,526],{},[424,628,629,638],{},[427,630,631],{},[430,632,633,636],{},[433,634,635],{},"Dataset",[433,637,618],{},[446,639,640,648,656],{},[430,641,642,645],{},[451,643,644],{},"Train",[451,646,647],{},"0.95",[430,649,650,653],{},[451,651,652],{},"Validation",[451,654,655],{},"0.87",[430,657,658,661],{},[451,659,660],{},"Test",[451,662,565],{},[363,664,665],{},"如果 Test dataset 的表現與 Validation dataset 相近，通常代表模型具有良好的泛化能力。",[401,667],{},[358,669,671],{"id":670},"如果沒有-validation-或-test-會發生什麼事","如果沒有 Validation 或 Test 會發生什麼事？",[363,673,674],{},"如果我們只使用 Train dataset，可能會發生兩個問題。",[363,676,677,678,370],{},"第一個問題是 ",[367,679,680],{},"模型選擇偏差（model selection bias）",[363,682,683],{},"如果沒有 validation dataset，我們就沒有一個客觀標準來比較不同模型設定，容易選到在訓練資料上表現很好，但實際上泛化能力很差的模型。",[363,685,686,687,370],{},"第二個問題是 ",[367,688,689],{},"評估過於樂觀（overly optimistic evaluation）",[363,691,692],{},"如果我們在訓練資料上評估模型，結果通常會高估模型的表現，因為模型已經「看過」這些資料。",[363,694,695],{},"因此在實務上，資料通常會按照以下比例切分：",[385,697,698,701,704],{},[388,699,700],{},"Train：70% ~ 80%",[388,702,703],{},"Validation：10% ~ 15%",[388,705,706],{},"Test：10% ~ 15%",[363,708,709,710,713],{},"在資料量較小的情況下，也可能使用 ",[367,711,712],{},"Cross Validation（交叉驗證）"," 來替代固定的 validation dataset。",[401,715],{},[358,717,718],{"id":718},"一個直觀的比喻",[363,720,721],{},"可以用「考試準備」來理解三種資料集的角色。",[385,723,724,729,734],{},[388,725,726,728],{},[367,727,390],{},"：平時做的練習題，用來學習知識。",[388,730,731,733],{},[367,732,393],{},"：模擬考，用來檢查自己是否準備好，並調整讀書策略。",[388,735,736,738],{},[367,737,396],{},"：正式考試，用來評估真正的能力。",[363,740,741],{},"如果你在模擬考後知道題目並重新背答案，那模擬考就不再是有效的評估工具。因此，正式考試必須是完全沒有看過的題目。",[401,743],{},[358,745,746],{"id":746},"結論",[363,748,749,750,753],{},"在機器學習中，將資料切分為 ",[367,751,752],{},"Train、Validation 與 Test dataset"," 是確保模型可靠性的重要步驟。Train dataset 用來讓模型學習資料中的模式，Validation dataset 用來調整模型與選擇最佳設定，而 Test dataset 則負責提供最客觀的最終評估。",[363,755,756],{},"透過這樣的資料切分方式，可以有效避免過度擬合與評估偏差，確保模型在真實世界中的表現更加可信。",{"title":758,"searchDepth":759,"depth":759,"links":760},"",2,[761,762,763,764,765,766,767],{"id":360,"depth":759,"text":361},{"id":405,"depth":759,"text":406},{"id":490,"depth":759,"text":491},{"id":591,"depth":759,"text":592},{"id":670,"depth":759,"text":671},{"id":718,"depth":759,"text":718},{"id":746,"depth":759,"text":746},"了解機器學習中資料切分的重要性，說明 Train、Validation 與 Test dataset 各自的角色與避免資料洩漏的方法。","md",null,{"tags":772,"category":86,"date":776},[86,773,774,775],"data_science","model_evaluation","dataset_split","2026-03-07",true,{"title":109,"description":768},"mDET2AZQMJY1JIr6dhFarybhlVpWCc7bkenrTDVck1c",[781,783],{"title":105,"path":106,"stem":107,"description":782,"children":-1},"從直觀概念到數學公式，深入理解 Logistic Regression 的原理，並透過實際案例了解它在分類問題中的應用。",{"title":113,"path":114,"stem":115,"description":784,"children":-1},"從 Boosting 概念開始，深入理解 XGBoost 的運作原理，並透過實際案例了解如何使用 XGBoost 建立高效的機器學習模型。",1776690842197]