[{"data":1,"prerenderedAt":46},["ShallowReactive",2],{"q-fintech-22-008":3},{"exam":4,"examName":5,"chapterSlug":6,"question":7,"related":22},"fintech","金融科技力知識檢定","c4",{"id":8,"exam":4,"session":9,"qno":10,"question":11,"options":12,"answer":17,"chapter":18,"freq":19,"explanation":20,"difficulty":21},"fintech-22-008","22",8,"在人工智慧系統中，哪種學習方法適用於標註數據進行訓練？",[13,14,15,16],"監督式學習","非監督式學習","強化學習","無監督學習",0,"人工智慧",1,"監督式學習以「已標註正確答案」的資料進行訓練,例如事先標明每筆交易是否為詐欺,讓模型學習輸入特徵與標籤之間的對應關係,再用來分類或預測新資料,故 (A) 正確。(B) 非監督式學習使用未標註資料,由模型自行找出分群或結構,如客戶分群;(D) 無監督學習只是非監督式學習的另一種譯名,同樣不需標註資料;(C) 強化學習則是讓代理人在環境中試誤,依獎勵與懲罰回饋調整策略,也不依賴標註資料集。","easy",[23,27,31,34,38,42],{"id":24,"question":25,"qno":26},"fintech-19-006","1980 年代人工智慧發展出的專家系統(Expert System)把取自專家的資訊彙編成一組規則，這些規則往往以「若...則...」結構呈現，稱為下列何種規則？",6,{"id":28,"question":29,"qno":30},"fintech-19-007","下列何種技術可以讓電腦模仿人類大腦的運算，讓電腦像人一樣思考？",7,{"id":32,"question":33,"qno":10},"fintech-19-008","有關機器學習訓練與預測的敘述，下列何者錯誤？",{"id":35,"question":36,"qno":37},"fintech-19-036","下列何種機器學習是所有資料都沒有標註，機器透過尋找資料的特徵，自己進行分類？",36,{"id":39,"question":40,"qno":41},"fintech-19-040","人工智慧使用運算晶片如 GPU，未來運用在特定人工智慧特定應用領域的專用晶片，稱為下列何者？",40,{"id":43,"question":44,"qno":45},"fintech-19-044","有關 2023 年推出新一代的語言模型 GPT-4 屬性之敘述，下列何者正確？",44,1793070565974]