{"resolved":true,"match_type":"uuid","source_type":"original_book","book_id":"cd4f7678-cd9b-4971-bde0-e9ad46a6cc71","title":"人工智能与大数据技术导论","author":null,"edition":null,"publisher":null,"year":null,"isbn":"9787302517986","requested_by":"printed_page","book":{"source_type":"original_book","book_id":"cd4f7678-cd9b-4971-bde0-e9ad46a6cc71","id":"cd4f7678-cd9b-4971-bde0-e9ad46a6cc71","uuid":"cd4f7678-cd9b-4971-bde0-e9ad46a6cc71","title":"人工智能与大数据技术导论","normalized_title":"人工智能与大数据技术导论","author":null,"edition":null,"publisher":null,"year":null,"isbn":"9787302517986","isbns":["9787302517986"],"parsed":true,"ai_readable":true,"document_type":"book","page_count":490,"navigation_url":"https://workshop.closeclaw.top/ai/book/cd4f7678-cd9b-4971-bde0-e9ad46a6cc71","title_url":"https://workshop.closeclaw.top/ai/title/%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD%E4%B8%8E%E5%A4%A7%E6%95%B0%E6%8D%AE%E6%8A%80%E6%9C%AF%E5%AF%BC%E8%AE%BA","fixed_page_url_template":"https://workshop.closeclaw.top/ai/book/cd4f7678-cd9b-4971-bde0-e9ad46a6cc71/page/{printed_page}","path_api_url_template":"https://workshop.closeclaw.top/api/ai/book/cd4f7678-cd9b-4971-bde0-e9ad46a6cc71/page/{printed_page}","read_url":"https://workshop.closeclaw.top/api/ai/read/cd4f7678-cd9b-4971-bde0-e9ad46a6cc71","page_url":"https://workshop.closeclaw.top/api/ai/books/cd4f7678-cd9b-4971-bde0-e9ad46a6cc71/page","search_url":"https://workshop.closeclaw.top/api/ai/books/cd4f7678-cd9b-4971-bde0-e9ad46a6cc71/search"},"page":{"printed_page":466,"pdf_page":482,"physical_index":482,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"2fb9018887bebff2b17fcc907c19c369276e5184184ef905cd473ef8020a082d"},"chapter":"第16章","content":"Q\n\n队列(queue)\n\n一种TensorFlow操作，用于实现队列数据结构，通常用于I/O中。\n\nR\n\n等级（rank）\n\n机器学习中的一个多含义术语，可以理解为下列含义之一：\n\n●张量中的维度数量。例如，标量等级为0，向量等级为1，矩阵等级为2。\n\n●在将类别从最高到最低进行排序的机器学习问题中，类别的顺序位置。例如，行为排序系统可以将小狗的奖励从最高（牛排）到最低（甘蓝）进行排序。\n\n评分者（rater）\n\n为样本提供标签的人，有时称为“注释者”。\n\n召回率(recall)\n\n一种分类模型指标，用于回答的问题是：在所有可能的正类别标签中，模型正确地识别出了多少个、即：\n\n$$\nA \\bot A B = \\frac { A B } { A C } ( A B \\bot A C ) ( A B \\bot A B \\bot C + B A \\bot A B \\bot A C )\n$$\n\n修正线性单元(ReLU,Rectified LinearUnit)\n\n一种激活函数，其规则如下：\n\n● 如果输入为负数或0，则输出0。\n\n●如果输入为正数，则输出等于输入。\n\n回归模型(regression model)\n\n一种模型，能够输出连续的值（通常为浮点值）。可与分类模型进行比较，分类模型输出离散值，例如“垃圾邮件”或“非垃圾邮件”。\n\n正则化（regularization）\n\n对模型复杂度的惩罚。正则化有助于防止出现过拟合，包含以下类型：\n\n● L1 正则化。\n\n●L2 正则化。\n\n●丢弃正则化。\n\n●早停法（这不是正式的正则化方法，但可以有效限制过拟合）。\n\n人工智能与大数据技术导论\n\n466","previous_page":465,"next_page":467}