{"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":469,"pdf_page":485,"physical_index":485,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"396aa08e421cf56d7738ad95b238815d371dbf555670b21bf2df669eb735ea0b"},"chapter":"第16章","content":"步(step）\n\n对一个批次的向前和向后评估。\n\n步长(step size)\n\n学习速率的同义词。\n\n随机梯度下降法(Stochastic Gradient Descent，SGD)\n\n批次大小为1的一种梯度下降法。换句话说，SGD依赖于从数据集中随机均匀选择的单个样本来计算每步的梯度估算值。\n\n结构风险最小化(Structural Risk Minimization，SRM)\n\n一种算法，用于平衡以下两个目标：\n\n●期望构建最具预测性的模型（例如损失最低）。\n\n●期望使模型尽可能简单（例如强大的正则化）。\n\n例如，旨在将基于训练集的损失和正则化降至最低的模型函数就是一种结构风险最小化算法。它与经验风险最小化相对。\n\n总结(summary）\n\n在TensorFlow中的某一步计算出的一个值或一组值，通常用于在训练期间跟踪模型指标。\n\n监督式机器学习(supervisedmachinelearning)\n\n根据输入数据及其对应的标签来训练模型。监督式机器学习类似于学生通过研究一系列问题及其对应的答案来学习某个主题。在掌握了问题和答案之间的对应关系后，学生便可以回答关于同一主题的新问题（以前从未见过的问题）。可与非监督式机器学习进行比较。\n\n合成特征(synthetic feature)\n\n一种特征，不在输入特征之列，而是从一个或多个输入特征衍生而来的。合成特征包括以下类型：\n\n●将一个特征与其本身或其他特征相乘（称为特征组合）。\n\n两个特征相除。\n\n●对连续特征进行分桶，以分为多个区间分箱。\n\n通过标准化或缩放单独创建的特征不属于合成特征。\n\n附录D 术语列表\n\n469","previous_page":468,"next_page":470}