https://terms-en.ai-term-hub.com/zh/tags/learning/Recent content in Learning on 中文AI术语词典Hugozh-cnSat, 18 Jul 2026 11:44:45 +0000https://terms-en.ai-term-hub.com/zh/terms/sample_complexity/Sat, 18 Jul 2026 11:32:54 +0000https://terms-en.ai-term-hub.com/zh/terms/sample_complexity/<h2 id="definition">Definition</h2> <p>在计算学习理论中，样本复杂度量化了有效训练模型所需的数据量。它平衡了模型容量与数据可用性之间的权衡，确保</p> <h3 id="summary">Summary</h3> <p>样本复杂度是指机器学习算法以高概率达到特定性能水平所需的训练样本数量。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>泛化误差</li> <li>训练数据规模</li> <li>收敛性</li> <li>防止过拟合</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>确定新模型的dataset需求</li> <li>比较不同学习算法的效率</li> <li>规划数据收集工作预算</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/vc%E7%BB%B4-vapnik-chervonenkis-dimension-%E8%A1%A1%E9%87%8F%E5%87%BD%E6%95%B0%E7%B1%BB%E5%A4%8D%E6%9D%82%E5%BA%A6%E7%9A%84%E6%8C%87%E6%A0%87/">VC维 (Vapnik-Chervonenkis dimension，衡量函数类复杂度的指标)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%81%8F%E5%B7%AE-%E6%96%B9%E5%B7%AE%E6%9D%83%E8%A1%A1-bias-variance-tradeoff-%E6%A8%A1%E5%9E%8B%E8%AF%AF%E5%B7%AE%E6%9D%A5%E6%BA%90%E7%9A%84%E5%B9%B3%E8%A1%A1/">偏差-方差权衡 (Bias-variance tradeoff，模型误差来源的平衡)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%B3%9B%E5%8C%96-generalization-%E6%A8%A1%E5%9E%8B%E5%AF%B9%E6%9C%AA%E8%A7%81%E6%95%B0%E6%8D%AE%E7%9A%84%E9%80%82%E5%BA%94%E8%83%BD%E5%8A%9B/">泛化 (Generalization，模型对未见数据的适应能力)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%95%B0%E6%8D%AE%E5%A2%9E%E5%BC%BA-data-augmentation-%E9%80%9A%E8%BF%87%E5%8F%98%E6%8D%A2%E5%A2%9E%E5%8A%A0%E8%AE%AD%E7%BB%83%E6%95%B0%E6%8D%AE%E5%A4%9A%E6%A0%B7%E6%80%A7%E7%9A%84%E6%8A%80%E6%9C%AF/">数据增强 (Data augmentation，通过变换增加训练数据多样性的技术)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/meta/Sat, 18 Jul 2026 11:25:49 +0000https://terms-en.ai-term-hub.com/zh/terms/meta/<h2 id="definition">Definition</h2> <p>在人工智能中，“元”前缀表示更高层次的抽象，通常涉及自我引用或对核心流程的监督。常见例子包括“元学习”，其中算法学习如何更快地学习新任务；以及“元优化”，即优化优化器本身的过程。它强调了对模型训练和调整机制的抽象管理。</p> <h3 id="summary">Summary</h3> <p>在 AI 中，“元”通常指关于学习的学习，或控制模型适应和优化的更高层级过程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>元学习</li> <li>高阶抽象</li> <li>自我引用</li> <li>适应性</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>少样本学习系统</li> <li>自动化机器学习 (AutoML)</li> <li>动态超参数调整</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/meta_learning-%E5%85%83%E5%AD%A6%E4%B9%A0/">meta_learning (元学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/few_shot_learning-%E5%B0%91%E6%A0%B7%E6%9C%AC%E5%AD%A6%E4%B9%A0/">few_shot_learning (少样本学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/hyperparameters-%E8%B6%85%E5%8F%82%E6%95%B0/">hyperparameters (超参数)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/optimization-%E4%BC%98%E5%8C%96/">optimization (优化)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/on_policy/Sat, 18 Jul 2026 10:56:59 +0000https://terms-en.ai-term-hub.com/zh/terms/on_policy/<h2 id="definition">Definition</h2> <p>在线策略算法要求智能体直接从其当前策略所采取的动作中学习。这意味着在探索过程中收集的数据被立即用于更新策略，从而确保数据分布的一致性。</p> <h3 id="summary">Summary</h3> <p>一种强化学习方法，其中被评估和改进的策略与用于生成数据的策略相同。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>强化学习</li> <li>策略梯度</li> <li>数据一致性</li> <li>样本效率</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>具有安全约束的机器人控制</li> <li>需要精确更新的博弈代理</li> <li>实时自适应系统</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/off-policy-%E7%A6%BB%E7%BA%BF%E7%AD%96%E7%95%A5/">off-policy (离线策略)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/reinforce-reinforce%E7%AE%97%E6%B3%95/">REINFORCE (REINFORCE算法)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/ppo-%E8%BF%91%E7%AB%AF%E7%AD%96%E7%95%A5%E4%BC%98%E5%8C%96/">PPO (近端策略优化)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/actor-critic-%E6%BC%94%E5%91%98-%E8%AF%84%E8%AE%BA%E5%AE%B6%E6%9E%B6%E6%9E%84/">actor-critic (演员-评论家架构)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/feedback/Sat, 18 Jul 2026 10:51:19 +0000https://terms-en.ai-term-hub.com/zh/terms/feedback/<h2 id="definition">Definition</h2> <p>反馈机制使AI系统能够从与用户或环境的交互中学习，从而优化未来的预测或行动。这包括强化学习信号、人在回路（human-in-the-loop）等机制。</p> <h3 id="summary">Summary</h3> <p>反馈涉及利用输出结果来迭代调整和改进AI模型或系统的性能。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>强化学习</li> <li>人在回路</li> <li>错误纠正</li> <li>迭代改进</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>推荐系统调优</li> <li>聊天机器人对话优化</li> <li>机器人控制调整</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/reinforcement-learning-%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0/">Reinforcement Learning (强化学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/supervised-learning-%E7%9B%91%E7%9D%A3%E5%AD%A6%E4%B9%A0/">Supervised Learning (监督学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/reward-function-%E5%A5%96%E5%8A%B1%E5%87%BD%E6%95%B0/">Reward Function (奖励函数)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/evolving/Sat, 18 Jul 2026 10:51:07 +0000https://terms-en.ai-term-hub.com/zh/terms/evolving/<h2 id="definition">Definition</h2> <p>“演进”一词描述了动态的人工智能模型，这些模型经历持续的学习和适应，而不是在初始训练后保持静态。这一概念是终身学习和在线学习系统的核心。</p> <h3 id="summary">Summary</h3> <p>描述通过新数据或反馈持续适应和改进的人工智能系统或算法。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>持续学习</li> <li>适应</li> <li>动态更新</li> <li>终身学习</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>更新用户偏好的推荐系统</li> <li>适应交通模式的自动驾驶汽车</li> <li>学习新诈骗手法的欺诈检测系统</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/online-learning-%E5%9C%A8%E7%BA%BF%E5%AD%A6%E4%B9%A0/">Online Learning (在线学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/drift-%E6%BC%82%E7%A7%BB/">Drift (漂移)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/adaptation-%E9%80%82%E5%BA%94/">Adaptation (适应)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/feedback-loop-%E5%8F%8D%E9%A6%88%E5%BE%AA%E7%8E%AF/">Feedback Loop (反馈循环)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/contrastive/Sat, 18 Jul 2026 10:49:42 +0000https://terms-en.ai-term-hub.com/zh/terms/contrastive/<h2 id="definition">Definition</h2> <p>这种方法鼓励模型在潜在空间中拉近正样本对（相似项）的嵌入表示，同时推远负样本对（不相似项）。它在计算机视觉和自然语言处理领域被广泛用于学习高质量的特征表示。</p> <h3 id="summary">Summary</h3> <p>对比学习是一种自监督技术，训练模型区分相似和不相似的数据对。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>嵌入向量</li> <li>正/负样本对</li> <li>损失函数</li> <li>自监督学习</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>图像检索系统</li> <li>语义搜索引擎</li> <li>人脸识别验证</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/siamese-networks-%E5%AD%AA%E7%94%9F%E7%BD%91%E7%BB%9C/">Siamese Networks (孪生网络)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/embedding-%E5%B5%8C%E5%85%A5/">Embedding (嵌入)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/representation-learning-%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0/">Representation Learning (表示学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/simclr-simclr%E7%AE%97%E6%B3%95/">SimCLR (SimCLR算法)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/bayesian/Sat, 18 Jul 2026 10:49:18 +0000https://terms-en.ai-term-hub.com/zh/terms/bayesian/<h2 id="definition">Definition</h2> <p>AI中的贝叶斯方法利用概率论，随着更多证据的出现来更新假设的可能性。这种方法允许模型量化不确定性并动态优化预测结果。</p> <h3 id="summary">Summary</h3> <p>指基于贝叶斯定理的统计方法，用于根据新证据更新概率。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>贝叶斯定理</li> <li>先验概率</li> <li>后验概率</li> <li>不确定性量化</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>垃圾邮件过滤</li> <li>医疗诊断系统</li> <li>A/B测试分析</li> </ul> <h2 id="code-example">Code Example</h2> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-python" data-lang="python"><span style="display:flex;"><span><span style="color:#f92672">from</span> sklearn.naive_bayes <span style="color:#f92672">import</span> GaussianNB </span></span><span style="display:flex;"><span>model <span style="color:#f92672">=</span> GaussianNB() </span></span><span style="display:flex;"><span>model<span style="color:#f92672">.</span>fit(X_train, y_train) </span></span></code></pre></div><h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/probability-%E6%A6%82%E7%8E%87/">Probability (概率)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/naive-bayes-%E6%9C%B4%E7%B4%A0%E8%B4%9D%E5%8F%B6%E6%96%AF/">Naive Bayes (朴素贝叶斯)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/inference-%E6%8E%A8%E6%96%AD/">Inference (推断)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/statistics-%E7%BB%9F%E8%AE%A1%E5%AD%A6/">Statistics (统计学)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/adaptive/Sat, 18 Jul 2026 10:49:06 +0000https://terms-en.ai-term-hub.com/zh/terms/adaptive/<h2 id="definition">Definition</h2> <p>在人工智能中，“自适应”描述的是能够根据新数据或环境反馈动态调整其内部状态、参数或策略的系统或算法。这种能力使模型……</p> <h3 id="summary">Summary</h3> <p>系统根据变化条件修改其行为或参数的能力。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>动态调整</li> <li>在线学习</li> <li>反馈回路</li> <li>个性化</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>推荐系统</li> <li>自适应控制系统</li> <li>实时异常检测</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/reinforcement-learning-%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0/">Reinforcement Learning (强化学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/online-learning-%E5%9C%A8%E7%BA%BF%E5%AD%A6%E4%B9%A0/">Online Learning (在线学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/meta-learning-%E5%85%83%E5%AD%A6%E4%B9%A0/">Meta-Learning (元学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/robustness-%E9%B2%81%E6%A3%92%E6%80%A7/">Robustness (鲁棒性)</a></li> </ul>