{"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":332,"pdf_page":348,"physical_index":348,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"9f24c88ea4ad33c1e83064a9acdf220cd32302c66dcc0b7fe32c283bc9e2e45b"},"chapter":"第10章","content":"下面进行线性缩放，即将输入标准化，以使其位于(-1,1)范围内，这可能是一种良好的标准做法。这样一来，SGD在一个维度中采用很大步长（或者在另一个维度中采用很小步长）时不会受阻。这种做法与使用预调节器（Preconditioner）的想法是有联系的。其代码如下：\n\n下面我们使用线性缩放将特征标准化，即将输入标准化到(-1.1)范围内。一般来说，当输入特征大致位于相同范围时，神经网络的训练效果最好。由于标准化会使用最小值和最大值，我们必须确保在整个数据集中一次性完成该操作。我们之所以可以这样做，是因为所有的数据都在一个DataFrame中。如果我们有多个数据集，那么最好从训练集中导出标准化参数，然后以相同的方式将其应用于测试集。其代码如下：\n\n工智能与大数据技术导论\n\n332","previous_page":331,"next_page":333}