{"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":465,"pdf_page":481,"physical_index":481,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"3d4ed170b2034d381a8014414b387486b62fca40da166310cc036ac8920b3584"},"chapter":"第16章","content":"困惑度与交叉熵的关系如下：\n\nP=2-cross entropy\n\n流水线(pipeline)\n\n机器学习算法的基础架构。流水线包括收集数据、将数据放入训练数据文件、训练一个或多个模型以及将模型导出到生产环境。\n\n正类别(positive class)\n\n在二元分类中，两种可能的类别分别被标记为正类别和负类别。正类别的结果是我们要测试的对象（不可否认的是，我们会同时测试这两种结果，但只关注正类别结果）。例如，在医学检查中，正类别可以是“肿瘤”；在电子邮件分类器中，正类别可以是“垃圾邮件”。\n\n与负类别相对。\n\n精确率（precision）\n\n一种分类模型指标。精确率指模型正确预测正类别的频率，即：\n\n$$\nA = A B = \\frac { A B } { A C } = \\frac { A B } { A B } \\times \\frac { 1 } { 2 } \\times \\frac { 1 } { 2 } \\times \\frac { 1 } { 2 } \\times \\frac { 1 } { 2 } \\times \\frac { 1 } { 2 } \\times \\frac { 1 } { 2 } = \\frac { 1 } { 2 } \\times \\frac { 1 } { 2 } \\times \\frac { 1 } { 2 } \\times \\frac { 1 } { 2 }\n$$\n\n预测（prediction）\n\n模型在收到输入的样本后的输出。\n\n预测偏差(prediction bias)\n\n一个值，用于表明预测平均值与数据集中标签的平均值相差有多大。\n\n预创建的 Estimator(pre-madeEstimator)\n\n其他人已建好的Estimator。TensorFlow提供了一些预创建的Estimator，包括DNNClassifier、DNNRegressor和LinearClassifier。你可以按照这些说明构建自已预创建的Estimator. 2\n\n预训练模型(pre-trained model)\n\n已经训练过的模型或模型组件（例如嵌套）。有时，你需要将预训练的嵌套馈送到神经网络。在其他时候，你的模型将自行训练嵌套，而不依赖于预训练的嵌套。\n\n先验信念(prior belief)\n\n在开始采用相应数据进行训练之前，你对这些数据抱有的信念。例如，L2正则化依赖的先验信念是权重应该很小且应以0为中心呈正态分布。\n\n附录D 术语列表\n\n465","previous_page":464,"next_page":466}