{"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":463,"pdf_page":479,"physical_index":479,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"c7a4bb23c317cf542b058476e1173a3bdff31cb7f9a00cb9bc58f6dc35cee58c"},"chapter":"第16章","content":"在特征工程过程中，你可能需要将这些字符串标识符编码为one-hot向量，向量的大小为15000。\n\n一对多(one-vs.-all)\n\n假设某个分类问题有N种可能的解决方案，一对多解决方案将包含N个单独的二元分类器，一个二元分类器对应一种可能的结果。例如，假设某个模型用于区分样本属于动物、蔬菜还是矿物，一对多解决方案将提供下列三个单独的二元分类器：\n\n动物和非动物。\n\n● 蔬菜和非蔬菜。\n\n矿物和非矿物。\n\n在线推断(online inference)\n\n根据需求生成预测。与离线推断相对。\n\n操作(Operation，op)\n\nTensorFlow图中的节点。在TensorFlow中，任何创建、操纵或销毁张量的过程都属于操作。例如，矩阵相乘就是一种操作，该操作以两个张量作为输入，并生成一个张量作为输出。\n\n优化器(optimizer)\n\n梯度下降法的一种具体实现。TensorFlow的优化器基类是tf.train.Optimizer。不同的优化器（tf.train.Optimizer的子类）会考虑如下概念：\n\n动量 (Momentum)。\n\n更新频率(AdaGrad=ADAptive GRADient descent; Adam = ADAptive with Momentum; RMSProp)\n\n●稀疏性/正则化（Ftrl）。\n\n●更复杂的计算方法（Proximal，等等）。\n\n甚至还包括NN驱动的优化器。\n\n离群值(outlier）\n\n与大多数其他值差别很大的值。在机器学习中，下列所有值都是离群值。\n\n绝对值很高的权重。\n\n●与实际值相差很大的预测值。\n\n● 值比平均值高大约3个标准偏差的输入数据。\n\n离群值常常会导致模型训练出现问题。\n\n输出层(output layer)\n\n神经网络的“最后”一层，也是包含答案的层。\n\n附录D 术语列表\n\n463","previous_page":462,"next_page":464}