{"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":455,"pdf_page":471,"physical_index":471,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"8e7e6d458072943a5be37d00bcc6578982327baffc7b79241158f5fe9bdca07e"},"chapter":"第16章","content":"完整softmax(full softmax)\n\n可参阅softmax。与候选采样相对。\n\n全连接层(fullyconnectedlayer)\n\n一种隐藏层，其中的每个节点均与下一个隐藏层中的每个节点相连。全连接层又称为密集层。\n\nG\n\n泛化(generalization)\n\n指的是模型依据训练时采用的数据，针对以前未见过的新数据做出正确预测的能力。\n\n广义线性模型(generalizedlinearmodel)\n\n最小二乘回归模型(基于高斯噪声）向其他类型的模型(基于其他类型的噪声，例如泊松噪声或分类噪声）进行的一种泛化。广义线性模型的示例包括：\n\n● 逻辑回归。\n\n●多类别回归。\n\n●最小二乘回归。\n\n可以通过凸优化找到广义线性模型的参数。广义线性模型具有以下特性：\n\n● 最优的最小二乘回归模型的平均预测结果等于训练数据的平均标签。\n\n●最优的逻辑回归模型预测的平均概率等于训练数据的平均标签。\n\n广义线性模型的功能受其特征的限制。与深度模型不同，广义线性模型无法“学习新特征”。\n\n梯度(gradient)\n\n偏导数相对于所有自变量的向量。在机器学习中，梯度是模型函数偏导数的向量。梯度指向最快上升的方向。\n\n梯度裁剪(gradient clipping)\n\n在应用梯度值之前先设置其上限。梯度裁剪有助于确保数值稳定性以及防止梯度爆炸。\n\n梯度下降法(gradient descent)\n\n一种通过计算并且减小梯度将损失降至最低的技术，它以训练数据为条件来计算损失相对于模型参数的梯度。通俗来说，梯度下降法以迭代方式调整参数，逐渐找到权重和偏差的最佳组合，从而将损失降至最低。\n\n图(graph)\n\nTensorFlow中的一种计算规范。图中的节点表示操作。边缘具有方向，表示将某项操作\n\n附录D 术语列表\n\n455","previous_page":454,"next_page":456}