https://answer.freetools.me/tags/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/ Recent content in 机器学习 on Answer Hugo -- 0.152.2 zh-cn Fri, 13 Mar 2026 01:59:53 +0800 https://answer.freetools.me/logit-lenstransformer%E7%9A%84%E6%AF%8F%E4%B8%80%E5%B1%82%E9%83%BD%E5%9C%A8%E6%83%B3%E4%BB%80%E4%B9%88/ Fri, 13 Mar 2026 01:59:53 +0800 https://answer.freetools.me/logit-lenstransformer%E7%9A%84%E6%AF%8F%E4%B8%80%E5%B1%82%E9%83%BD%E5%9C%A8%E6%83%B3%E4%BB%80%E4%B9%88/ 深入解析Logit Lens和Tuned Lens技术如何将Transformer中间层的隐藏状态解码为可理解的词汇预测，揭示大语言模型的逐层推理过程、应用场景与技术局限。 https://answer.freetools.me/%E5%BD%9399%E5%87%86%E7%A1%AE%E7%8E%87%E6%88%90%E4%B8%BA%E8%B0%8E%E8%A8%80%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E8%AF%84%E4%BC%B0%E6%8C%87%E6%A0%87%E7%9A%84%E6%B7%B1%E5%B1%82%E5%8D%9A%E5%BC%88/ Thu, 12 Mar 2026 21:08:27 +0800 https://answer.freetools.me/%E5%BD%9399%E5%87%86%E7%A1%AE%E7%8E%87%E6%88%90%E4%B8%BA%E8%B0%8E%E8%A8%80%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E8%AF%84%E4%BC%B0%E6%8C%87%E6%A0%87%E7%9A%84%E6%B7%B1%E5%B1%82%E5%8D%9A%E5%BC%88/ 从混淆矩阵的数学根基出发，系统解析准确率、精确率、召回率、F1-score等分类指标的本质与局限，深入剖析ROC/PR曲线与AUC的工作原理，揭示为何准确率会在不平衡数据上"说谎"，以及医疗诊断、欺诈检测等场景中如何正确选择评估指标。 https://answer.freetools.me/%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0%E5%85%A8%E6%99%AF%E8%A7%A3%E6%9E%90%E4%BB%8Emse%E5%88%B0focal-loss%E5%A6%82%E4%BD%95%E4%B8%BA%E4%B8%8D%E5%90%8C%E4%BB%BB%E5%8A%A1%E9%80%89%E6%8B%A9%E6%AD%A3%E7%A1%AE%E7%9A%84%E4%BC%98%E5%8C%96%E7%9B%AE%E6%A0%87/ Thu, 12 Mar 2026 15:25:03 +0800 https://answer.freetools.me/%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0%E5%85%A8%E6%99%AF%E8%A7%A3%E6%9E%90%E4%BB%8Emse%E5%88%B0focal-loss%E5%A6%82%E4%BD%95%E4%B8%BA%E4%B8%8D%E5%90%8C%E4%BB%BB%E5%8A%A1%E9%80%89%E6%8B%A9%E6%AD%A3%E7%A1%AE%E7%9A%84%E4%BC%98%E5%8C%96%E7%9B%AE%E6%A0%87/ 深入解析深度学习中各类损失函数的数学原理、梯度推导与应用场景。从回归任务的MSE、MAE、Huber Loss，到分类任务的交叉熵、Focal Loss，再到度量学习的Triplet Loss与Contrastive Loss，系统阐述如何根据任务特性选择正确的优化目标。 https://answer.freetools.me/%E4%BA%A4%E5%8F%89%E7%86%B5%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0%E4%B8%BA%E4%BB%80%E4%B9%88%E8%BF%99%E4%B8%AA%E5%85%AC%E5%BC%8F%E7%BB%9F%E6%B2%BB%E4%BA%86%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E7%9A%84%E6%A6%82%E7%8E%87%E9%A2%84%E6%B5%8B/ Wed, 11 Mar 2026 22:38:36 +0800 https://answer.freetools.me/%E4%BA%A4%E5%8F%89%E7%86%B5%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0%E4%B8%BA%E4%BB%80%E4%B9%88%E8%BF%99%E4%B8%AA%E5%85%AC%E5%BC%8F%E7%BB%9F%E6%B2%BB%E4%BA%86%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E7%9A%84%E6%A6%82%E7%8E%87%E9%A2%84%E6%B5%8B/ 从信息论的自信息概念出发，深入解析交叉熵损失函数的数学原理、梯度推导、与最大似然估计的等价性，以及在大语言模型训练中的核心作用。涵盖熵、KL散度、困惑度、数值稳定性、标签平滑等关键技术细节。 https://answer.freetools.me/%E9%9B%B6%E8%AE%AD%E7%BB%83%E6%88%90%E6%9C%AC%E7%9A%84%E5%A4%9A%E4%BB%BB%E5%8A%A1%E8%9E%8D%E5%90%88%E4%BB%8Etask-arithmetic%E5%88%B0ties-merging%E7%9A%84%E6%A8%A1%E5%9E%8B%E5%90%88%E5%B9%B6%E9%9D%A9%E5%91%BD/ Mon, 09 Mar 2026 06:46:30 +0800 https://answer.freetools.me/%E9%9B%B6%E8%AE%AD%E7%BB%83%E6%88%90%E6%9C%AC%E7%9A%84%E5%A4%9A%E4%BB%BB%E5%8A%A1%E8%9E%8D%E5%90%88%E4%BB%8Etask-arithmetic%E5%88%B0ties-merging%E7%9A%84%E6%A8%A1%E5%9E%8B%E5%90%88%E5%B9%B6%E9%9D%A9%E5%91%BD/ 零训练成本的多任务融合：从Task Arithmetic到TIES-Merging的模型合并革命 https://answer.freetools.me/%E5%9E%83%E5%9C%BE%E9%82%AE%E4%BB%B6%E8%BF%87%E6%BB%A4%E7%9A%84%E4%B8%89%E5%8D%81%E5%B9%B4%E6%88%98%E4%BA%89%E4%BB%8E%E8%A7%84%E5%88%99%E5%BC%95%E6%93%8E%E5%88%B0%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E8%BF%9B%E5%8C%96%E4%B9%8B%E8%B7%AF/ Fri, 06 Mar 2026 07:26:58 +0800 https://answer.freetools.me/%E5%9E%83%E5%9C%BE%E9%82%AE%E4%BB%B6%E8%BF%87%E6%BB%A4%E7%9A%84%E4%B8%89%E5%8D%81%E5%B9%B4%E6%88%98%E4%BA%89%E4%BB%8E%E8%A7%84%E5%88%99%E5%BC%95%E6%93%8E%E5%88%B0%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E8%BF%9B%E5%8C%96%E4%B9%8B%E8%B7%AF/ 深入解析垃圾邮件过滤技术的三十年演进。从1978年第一封垃圾邮件的诞生，到Paul Graham 2002年的贝叶斯革命，再到Gmail使用TensorFlow实现99.9%拦截率。系统梳理规则引擎、统计过滤、机器学习、深度学习四代技术架构的更迭，揭示这场没有硝烟的战争背后的技术逻辑与攻防博弈。