{"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":203,"pdf_page":219,"physical_index":219,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"5a277ea638f93ca817068bb46d518823f5269fbc89aebe36bf477dbcd861d904"},"chapter":"第7章","content":"7.4.1 卷积运算\n\n卷积运算是卷积神经网络中的核心演算步骤。卷积运算是将一个矩阵和另一个“矩阵乘子”通过特定规则计算出一个新的矩阵的过程。这个“矩阵乘子”叫作卷积核（Filter）。比如一个5\\*5的矩阵和一个3\\*3的卷积核进行卷积，可以得到一个3\\*3的矩阵，如图7-13所示。\n\n卷积运算按照下述方式进行：首先，根据卷积核的规格，对应原矩阵左上角的矩阵。在这个例子中，是如图7-14所示的3\\*3的矩阵。\n\n将选中的矩阵和卷积核矩阵“相乘”。这里的乘指的是对应元素相乘，然后求和，将得到的数放入矩阵的左上角，如图7-15所示。\n\n$$\n3 ^ { * } 1 + 3 ^ { * } 1 + 0 ^ { * } 0 + 5 ^ { * } 2 + 2 ^ { * } 0 + 2 ^ { * } ~ ( - 1 ) ~ + 2 ^ { * } ~ ( - 2 ) ~ + 2 ^ { * } 1 + 0 ^ { * } 3 = 1 2\n$$\n\n这样我们就得到了卷积矩阵中的一个元素。然后将原矩阵的选定区域平移，放到如图7-16所示的位置。\n\n第7章 深度学习\n\n7.4\n\n卷积神经网络\n\n203","previous_page":202,"next_page":204}