{"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":322,"pdf_page":338,"physical_index":338,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"226ce862b53e07eceeaf7a32fa7c224d0a96adce3c03be7c64a466c3f8cc02b1"},"chapter":"第10章","content":"f(x),即 $\\scriptstyle \\mathbf { y } = \\mathbf { f } ( \\mathbf { x } )$ 。使用这两个公式，我们可以传播到网络的其余节点，并获得网络的最终输出(一直到最顶端)。\n\n$$\ny = f ( x )\n$$\n\n$$\nx _ { j } = \\sum _ { i \\in i n ( j ) } w _ { i j } y _ { i } + b _ { j }\n$$\n\n10.2.2 反向传播算法\n\n在讲解反向传播算法之前，我们先说明一下误差导数。反向传播算法会对特定样本的预测输出和理想输出进行比较，然后确定网络的每个权重的更新幅度。为此，需要计算误差相对于每个权重的变化情况 $\\big ( \\frac { d E } { d w _ { i j } } \\big )$ 。获得误差导数后，可以使用一种简单的更新法则来更新权重：\n\n$$\nw _ { i j } = w _ { i j } - \\alpha \\frac { d E } { d w _ { i j } }\n$$\n\n其中， $\\mathrm { a }$ 是一个正常量，称为“学习速率”，我们需要根据经验对该常量进行微调。该更新法则非常简单：如果在权重提高后误差降低了 $( \\ \\frac { d E } { d w _ { i j } } < 0 )$ ，则提高权重；如果在权重提高后误差也提高了 $( \\ \\frac { d E } { d w _ { i j } } > 0 )$ ，则降低权重。如图10-18所示，每个权重的连线上都加了误差导数。\n\n人工智能与大数据技术导论\n\n322","previous_page":321,"next_page":323}