{"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":230,"pdf_page":246,"physical_index":246,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"21581b5bb6e61126a4d339c07033992c53a430ec32feea6a03ec931df3f2eca2"},"chapter":"第8章","content":"人工智能与大数据技术导论\n\n训练误差应该持续减小，这个误差曲线开始时可能比较陡，但是最终平稳(这时训练收敛）。\n\n●如果训练没有收敛，训练时间可以更长一点。\n\n如果训练误差下降得很慢，可以尝试加大步长。但要注意，有时步长过大，会有反作用。\n\n●如果训练误差上下起伏很大，可以尝试减少步长。除了减少步长外，还要增加步数和批处理大小。\n\n●小的批处理有时会不太稳定。可以先尝试100或1000，然后逐步减少，直到看到降级。\n\n有时，我们也可以变换特征参数，比如：\n\n相关数据如图8-23、图8-24所示。\n\n230","previous_page":229,"next_page":231}