{"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":447,"pdf_page":463,"physical_index":463,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"d489f493c9fc206d5291c5d4c85b916195f3101fa63155c00df58ab0294639de"},"chapter":"第16章","content":"基准(baseline)\n\n一种简单的模型或启发法，用作比较模型效果时的参考点。基准有助于模型开发者针对特定问题量化最低预期效果。\n\n批次（batch）\n\n模型训练的一次迭代（一次梯度更新）中使用的样本集。\n\n批次大小(batch size)\n\n一个批次中的样本数。例如，SGD的批次大小为1，而小批次的大小通常介于10到1000之间。批次大小在训练和推断期间通常是固定的；不过，TensorFlow允许使用动态批次大小。\n\n偏差（bias）\n\n距离原点的截距或偏移。偏差（也称为偏差项）在机器学习模型中以b或w0表示。例如，在下面的公式中，偏差为b:\n\n$$\n\\mathbf { y } ^ { \\prime } { = } \\mathbf { b } { + } \\mathbf { w } _ { 1 } \\mathbf { x } _ { 1 } { + } \\mathbf { w } _ { 2 } \\mathbf { x } _ { 2 } { + } \\ldots { + } \\mathbf { w } _ { \\mathrm { n } } \\mathbf { x } _ { \\mathrm { n } }\n$$\n\n请勿与预测偏差混淆。\n\n二元分类(binaryclassification)\n\n一种分类任务，可输出两种互斥类别之一。例如，对电子邮件进行评估并输出“垃圾邮件”或“非垃圾邮件”的机器学习模型就是一个二元分类器。\n\n分箱(binning)\n\n可参阅分桶。\n\n分桶(bucketing）\n\n将一个特征（通常是连续特征）转换成多个二元特征（称为桶或箱），通常根据值区间进行转换。例如，你可以将温度区间分割为离散分箱，而不是将温度表示成单个连续的浮点特征。假设温度数据可精确到小数点后一位，则可以将介于0.0度到15.0度之间的所有温度都归入一个分箱，将介于15.1度到30.0度之间的所有温度归入第二个分箱，并将介于30.1度到50.0度之间的所有温度归入第三个分箱。\n\nC\n\n校准层(calibration layer)\n\n一种预测后调整，通常是为了降低预测偏差。调整后的预测和概率应与观察到的标签集的分布一致。\n\n附录D 术语列表\n\n447","previous_page":null,"next_page":448}