{"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":464,"pdf_page":480,"physical_index":480,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"e6c0398aa5663a30569e8d7f8c0d57cccf412a0ee42f11d9e2661db486cb22fa"},"chapter":"第16章","content":"人工智能与大数据技术导论\n\n过拟合（overfitting）\n\n创建的模型与训练数据过于匹配，以至于模型无法根据新数据做出正确的预测。\n\nP\n\nPandas\n\n面向列的数据分析API。很多机器学习框架（包括TensorFlow）都支持将Pandas数据结构作为输入。可参阅Pandas文档。\n\n参数(parameter）\n\n机器学习系统自行训练的模型的变量。例如，权重就是一种参数，它们的值是机器学习系统通过连续的训练迭代逐渐学习到的。与超参数相对。\n\n参数服务器(Parameter Server，PS)\n\n一种作业，负责在分布式设置中跟踪模型参数。\n\n参数更新（parameter update)\n\n在训练期间（通常是在梯度下降法的单次迭代中）调整模型参数的操作。\n\n偏导数(partial derivative)\n\n一种导数，除了一个变量之外的所有变量都被视为常量。例如，f(x,y)对x的偏导数就是f(x)的导数（即使y保持恒定）。f对x的偏导数仅关注x如何变化，而忽略公式中的所有其他变量。\n\n分区策略（partitioning strategy）\n\n参数服务器中分割变量的算法。\n\n性能（performance）\n\n多含义术语，具有以下含义：\n\n●在软件工程中的传统含义，即相应软件的运行速度有多快（或有多高效）。\n\n●在机器学习中的含义。在机器学习领域，性能旨在回答的问题是，相应模型的准确度有多高，即模型在预测方面的表现得有多好。\n\n困惑度(perplexity)\n\n一种衡量指标，用于衡量模型能够多好地完成任务。例如，假设任务是读取用户使用智能手机键盘输入字词时输入的前几个字母，然后列出一组可能的完整字词。此任务的困惑度(P)是，为了使列出的字词中包含用户尝试输入的实际字词，你需要提供猜测项的个数。\n\n464","previous_page":463,"next_page":465}