{"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":342,"pdf_page":358,"physical_index":358,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"605cf8cb7e78ddc0cd475efa9c169a8b5e1bd34d36f1399075b4f71ec0c0d7a8"},"chapter":"第10章","content":"以某图片分析为例，Softmax可能会得出图片属于某一特定类别的概率，如表10-1所示。\n\nSoftmax层是紧挨着输出层，并在输出层之前的神经网络层。Softmax层必须和输出层拥有一样的节点数（见图10-38）。\n\nSoftmax方程式如下：\n\n$$\np ( y = j | \\mathbf { x } ) = \\frac { e ^ { ( \\mathbf { w } _ { j } ^ { T } \\mathbf { x } + b _ { j } ) } } { \\sum _ { k \\in K } e ^ { ( \\mathbf { w } _ { k } ^ { T } \\mathbf { x } + b _ { k } ) } }\n$$\n\n此公式本质上是将逻辑回归公式延伸到了多类别。以下是Softmax的变体：\n\n完整Softmax是我们一直以来讨论的 Softmax，也就是说，Softmax针对每个可能的类别计算概率。\n\n候选采样指Softmax针对所有正类别标签计算概率，但仅针对负类别标签的随机样本计算概率。例如，如果想要确定某张输入图片是波音737飞机还是波音747飞机的图片，就不必针对每个非飞机样本提供概率。类别数量较少时，完整Softmax代价很小，但随着类别数量的增加，代价会变得极其高昂。候选采样可以提高处理具有大量类别问题的效率。\n\n●Softmax假设每个样本只是一个类别的成员。但是，一些样本可以同时是多个类别的成员。对于此类示例：\n\n人工智能与大数据技术导论\n\n342","previous_page":341,"next_page":343}