https://terms-en.ai-term-hub.com/zh/tags/algorithms/Recent content in Algorithms 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/tree_of_thoughts/Sat, 18 Jul 2026 11:37:15 +0000https://terms-en.ai-term-hub.com/zh/terms/tree_of_thoughts/<h2 id="definition">Definition</h2> <p>思维树（ToT）通过允许模型在每个步骤中探索多个不同的推理路径并形成树状结构，扩展了传统的思维链提示方法。模型会对这些路径进行评估，以决定后续行动。</p> <h3 id="summary">Summary</h3> <p>思维树是一种推理框架，它同时探索多种可能的推理路径，并通过评估这些路径来选择最有希望的下一步。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>搜索算法</li> <li>回溯</li> <li>状态评估</li> <li>推理路径</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>复杂数学问题求解</li> <li>创意写作生成</li> <li>策略性游戏对弈</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/chain-of-thought-%E6%80%9D%E7%BB%B4%E9%93%BE/">Chain of Thought (思维链)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/beam-search-%E6%9D%9F%E6%90%9C%E7%B4%A2/">Beam Search (束搜索)</a></li> <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/reasoning-%E6%8E%A8%E7%90%86/">Reasoning (推理)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/quantum_machine_learning/Sat, 18 Jul 2026 11:31:12 +0000https://terms-en.ai-term-hub.com/zh/terms/quantum_machine_learning/<h2 id="definition">Definition</h2> <p>量子机器学习（QML）是一个新兴的跨学科领域，它将量子计算能力与机器学习技术相结合。其目的是利用量子现象（如纠缠和叠加）来加速数据处理和模型训练，从而在特定任务上实现超越经典计算机的性能。</p> <h3 id="summary">Summary</h3> <p>量子机器学习将量子计算与机器学习算法相结合，以更快速或更高效地解决问题。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>量子算法</li> <li>混合系统</li> <li>指数级加速</li> <li>量子核方法</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>分子模拟</li> <li>金融投资组合优化</li> <li>高维数据分类</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%8F%98%E5%88%86%E9%87%8F%E5%AD%90%E6%9C%AC%E5%BE%81%E6%B1%82%E8%A7%A3%E5%99%A8-variational-quantum-eigensolver/">变分量子本征求解器 (Variational Quantum Eigensolver)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E9%87%8F%E5%AD%90%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C-quantum-neural-networks/">量子神经网络 (Quantum Neural Networks)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/qiskit/">Qiskit</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/object_detection/Sat, 18 Jul 2026 11:28:35 +0000https://terms-en.ai-term-hub.com/zh/terms/object_detection/<h2 id="definition">Definition</h2> <p>目标检测扩展了图像分类的功能，不仅确定存在哪些对象，还确定它们的位置。它输出检测到的项目周围的边界坐标及其类别标签。</p> <h3 id="summary">Summary</h3> <p>一种计算机视觉技术，使用边界框在图像或视频流中识别并定位目标对象。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>边界框</li> <li>类别标签</li> <li>YOLO</li> <li>Faster R-CNN</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>自动驾驶导航</li> <li>零售库存管理</li> <li>安防摄像头监控</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%9B%BE%E5%83%8F%E5%88%86%E7%B1%BB/">图像分类</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E8%AF%AD%E4%B9%89%E5%88%86%E5%89%B2/">语义分割</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/">计算机视觉</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/maximum_inner_product_search/Sat, 18 Jul 2026 11:25:49 +0000https://terms-en.ai-term-hub.com/zh/terms/maximum_inner_product_search/<h2 id="definition">Definition</h2> <p>最大内积搜索（MIPS）是信息检索和机器学习中的一个基本问题，尤其在推荐系统中应用广泛。与衡量余弦相似度的标准搜索不同，MIPS 旨在最大化向量间的点积值，这通常能更准确地反映用户偏好或项目相关性，特别是在处理非归一化向量时。</p> <h3 id="summary">Summary</h3> <p>一种专门的向量相似度搜索技术，用于检索与查询向量具有最高点积（内积）的项目。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>点积</li> <li>向量相似度</li> <li>推荐系统</li> <li>近似最近邻</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>个性化产品推荐</li> <li>基于流行度的内容排序</li> <li>带有偏差校正的语义搜索</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/cosine_similarity-%E4%BD%99%E5%BC%A6%E7%9B%B8%E4%BC%BC%E5%BA%A6/">cosine_similarity (余弦相似度)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/vector_database-%E5%90%91%E9%87%8F%E6%95%B0%E6%8D%AE%E5%BA%93/">vector_database (向量数据库)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/nearest_neighbor_search-%E6%9C%80%E8%BF%91%E9%82%BB%E6%90%9C%E7%B4%A2/">nearest_neighbor_search (最近邻搜索)</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> </ul>https://terms-en.ai-term-hub.com/zh/terms/lifelong_planning_a/Sat, 18 Jul 2026 11:24:07 +0000https://terms-en.ai-term-hub.com/zh/terms/lifelong_planning_a/<h2 id="definition">Definition</h2> <p>终身规划A*（LPA*）是为成本随时间变化的环境设计的A<em>搜索算法的扩展。与重新启动搜索不同，LPA</em>维护一个优先级队列并仅更新受更改影响的节点，从而显著提高了在动态图环境中重新规划路径的效率。</p> <h3 id="summary">Summary</h3> <p>一种增量式路径查找算法，能够在边权重发生变化后，无需从头重新计算即可高效地更新最短路径。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>增量搜索</li> <li>路径查找</li> <li>动态图</li> <li>机器人导航</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>交通中的自动驾驶车辆路线规划</li> <li>变化仓库中的机器人导航</li> <li>实时战略游戏中的AI移动</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/a_star-a-%E7%AE%97%E6%B3%95/">a_star (A*算法)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/d_star-d-%E7%AE%97%E6%B3%95/">d_star (D*算法)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/incremental_search-%E5%A2%9E%E9%87%8F%E6%90%9C%E7%B4%A2/">incremental_search (增量搜索)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/path_planning-%E8%B7%AF%E5%BE%84%E8%A7%84%E5%88%92/">path_planning (路径规划)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/lazy_learning/Sat, 18 Jul 2026 11:23:41 +0000https://terms-en.ai-term-hub.com/zh/terms/lazy_learning/<h2 id="definition">Definition</h2> <p>惰性学习者（如k近邻算法）会记住整个训练数据集，仅在做出预测时才进行计算。这与急切学习形成对比，后者会在训练阶段构建一个通用模型。</p> <h3 id="summary">Summary</h3> <p>一种学习方法，将泛化推迟到分类时才进行，存储训练实例而不是构建显式模型。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>基于实例的学习</li> <li>k近邻算法</li> <li>推理成本</li> <li>泛化</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>推荐系统</li> <li>小数据集的模式识别</li> <li>预测模型的原型设计</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.neighbors <span style="color:#f92672">import</span> KNeighborsClassifier </span></span><span style="display:flex;"><span>clf <span style="color:#f92672">=</span> KNeighborsClassifier(n_neighbors<span style="color:#f92672">=</span><span style="color:#ae81ff">5</span>) </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/instance_based_learning-%E5%9F%BA%E4%BA%8E%E5%AE%9E%E4%BE%8B%E7%9A%84%E5%AD%A6%E4%B9%A0/">instance_based_learning (基于实例的学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/knn-k%E8%BF%91%E9%82%BB%E7%AE%97%E6%B3%95/">knn (k近邻算法)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/eager_learning-%E6%80%A5%E5%88%87%E5%AD%A6%E4%B9%A0/">eager_learning (急切学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/generalization-%E6%B3%9B%E5%8C%96/">generalization (泛化)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/hierarchical_navigable_small_world/Sat, 18 Jul 2026 11:20:58 +0000https://terms-en.ai-term-hub.com/zh/terms/hierarchical_navigable_small_world/<h2 id="definition">Definition</h2> <p>分层可导航小世界（HNSW）算法构建了一个多层图结构，其中每一层包含下一层节点的子集。导航从顶层开始，逐步向下移动到更详细的层级，直到找到最近的邻居。这种方法结合了小世界网络的快速收敛特性和分层结构的效率，实现了高维向量的高效近似最近邻搜索。</p> <h3 id="summary">Summary</h3> <p>一种基于图的数据结构，用于在高维空间中实现高效的近似最近邻搜索。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>图搜索</li> <li>近似最近邻</li> <li>多层图</li> <li>对数复杂度</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>向量搜索</li> <li>推荐引擎</li> <li>图像检索</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/k-nearest-neighbors-k%E8%BF%91%E9%82%BB/">K-Nearest Neighbors (K近邻)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/faiss-facebook-ai-similarity-search%E5%BA%93/">Faiss (Facebook AI Similarity Search库)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/annoy-spotify%E5%BC%80%E5%8F%91%E7%9A%84%E8%BF%91%E4%BC%BC%E6%9C%80%E8%BF%91%E9%82%BB%E5%BA%93/">Annoy (Spotify开发的近似最近邻库)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/extremal_optimization/Sat, 18 Jul 2026 11:16:49 +0000https://terms-en.ai-term-hub.com/zh/terms/extremal_optimization/<h2 id="definition">Definition</h2> <p>与维持种群的遗传算法不同，EO作用于单个解。它识别对整体适应度贡献最小的组件，并用随机替代方案替换它。</p> <h3 id="summary">Summary</h3> <p>极值优化是一种受自组织临界性启发的启发式搜索算法，旨在通过迭代移除表现最差的组件来解决组合优化问题。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>启发式搜索</li> <li>组合优化</li> <li>自组织临界性</li> <li>局部改进</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>图划分问题</li> <li>计算集群中的任务调度</li> <li>优化网络路由路径</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E9%81%97%E4%BC%A0%E7%AE%97%E6%B3%95/">遗传算法</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%A8%A1%E6%8B%9F%E9%80%80%E7%81%AB/">模拟退火</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E7%B2%92%E5%AD%90%E7%BE%A4%E4%BC%98%E5%8C%96/">粒子群优化</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%85%83%E5%90%AF%E5%8F%91%E5%BC%8F%E7%AE%97%E6%B3%95/">元启发式算法</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/discovery_system/Sat, 18 Jul 2026 11:15:21 +0000https://terms-en.ai-term-hub.com/zh/terms/discovery_system/<h2 id="definition">Definition</h2> <p>发现系统是一种计算框架，旨在通过自动化探索庞大的数据空间来加速科学或分析突破。与传统仅寻求局部最优的优化不同，发现系统致力于在整个搜索空间中进行广泛探索，以识别新颖的模式或假设。</p> <h3 id="summary">Summary</h3> <p>一种旨在识别、探索和评估大型搜索空间中潜在解决方案、模式或假设的自动化框架或算法流程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>自动化探索</li> <li>假设生成</li> <li>主动学习</li> <li>搜索空间导航</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>识别制药领域的新分子结构</li> <li>发现具有特定属性的新材料</li> <li>在大型数据集中发现意外的相关性</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/automated-machine-learning-%E8%87%AA%E5%8A%A8%E5%8C%96%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/">Automated Machine Learning (自动化机器学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/scientific-discovery-%E7%A7%91%E5%AD%A6%E5%8F%91%E7%8E%B0/">Scientific Discovery (科学发现)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/bayesian-optimization-%E8%B4%9D%E5%8F%B6%E6%96%AF%E4%BC%98%E5%8C%96/">Bayesian Optimization (贝叶斯优化)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/data-mining-%E6%95%B0%E6%8D%AE%E6%8C%96%E6%8E%98/">Data Mining (数据挖掘)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/differentially_private_stochastic_gradient_descent/Sat, 18 Jul 2026 11:14:55 +0000https://terms-en.ai-term-hub.com/zh/terms/differentially_private_stochastic_gradient_descent/<h2 id="definition">Definition</h2> <p>DP-SGD 是随机梯度下降的一种变体，旨在保护训练数据的隐私。它通过裁剪每个样本梯度的贡献来限制敏感度，然后添加高斯噪声来实现隐私保护。</p> <h3 id="summary">Summary</h3> <p>一种优化算法，通过对标准随机梯度下降（SGD）进行梯度裁剪和添加噪声的修改，确保训练后的模型满足差分隐私约束。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>梯度裁剪</li> <li>高斯噪声注入</li> <li>样本子采样</li> <li>隐私会计</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>在私有用户数据上训练深度神经网络</li> <li>医疗保健预测建模</li> <li>使用受监管数据进行金融欺诈检测</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%B7%AE%E5%88%86%E9%9A%90%E7%A7%81-differential-privacy/">差分隐私 (Differential Privacy)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E9%9A%8F%E6%9C%BA%E6%A2%AF%E5%BA%A6%E4%B8%8B%E9%99%8D-sgd/">随机梯度下降 (SGD)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%A8%A1%E5%9E%8B%E5%8F%8D%E8%BD%AC%E6%94%BB%E5%87%BB-model-inversion-attacks/">模型反转攻击 (Model Inversion Attacks)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E9%9A%90%E7%A7%81%E9%A2%84%E7%AE%97-privacy-budget/">隐私预算 (Privacy Budget)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/cross_entropy_method/Sat, 18 Jul 2026 11:12:12 +0000https://terms-en.ai-term-hub.com/zh/terms/cross_entropy_method/<h2 id="definition">Definition</h2> <p>交叉熵法（CEM）是一种强大的通用优化算法，用于解决离散和连续问题。它通过维护搜索空间上的概率分布来工作，并通过迭代更新该分布以聚焦于高性能样本，从而逐步优化解决方案。</p> <h3 id="summary">Summary</h3> <p>一种随机优化技术，利用蒙特卡洛模拟迭代改进对罕见事件概率的估计。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>蒙特卡洛模拟</li> <li>迭代优化</li> <li>概率分布更新</li> <li>精英样本</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>机器人路径规划</li> <li>游戏AI策略优化</li> <li>风险分析中的罕见事件估计</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/simulated-annealing-%E6%A8%A1%E6%8B%9F%E9%80%80%E7%81%AB/">Simulated Annealing (模拟退火)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/genetic-algorithms-%E9%81%97%E4%BC%A0%E7%AE%97%E6%B3%95/">Genetic Algorithms (遗传算法)</a></li> <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> </ul>https://terms-en.ai-term-hub.com/zh/terms/computational_heuristic_intelligence/Sat, 18 Jul 2026 11:10:50 +0000https://terms-en.ai-term-hub.com/zh/terms/computational_heuristic_intelligence/<h2 id="definition">Definition</h2> <p>计算启发式智能涉及采用经验法则、近似值或合理猜测，在合理时间内找到令人满意的解决方案的算法。与穷举搜索不同，它侧重于效率而非绝对最优解。</p> <h3 id="summary">Summary</h3> <p>当精确方法过于缓慢时，使用基于经验和实用技巧来高效解决问题的AI方法。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>近似</li> <li>经验法则</li> <li>搜索优化</li> <li>时间复杂度</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>物流路线规划</li> <li>国际象棋和围棋引擎走法</li> <li>云计算中的资源分配</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/genetic-algorithms-%E9%81%97%E4%BC%A0%E7%AE%97%E6%B3%95/">Genetic Algorithms (遗传算法)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/simulated-annealing-%E6%A8%A1%E6%8B%9F%E9%80%80%E7%81%AB/">Simulated Annealing (模拟退火)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/a-search-a-%E6%90%9C%E7%B4%A2%E7%AE%97%E6%B3%95/">A* Search (A*搜索算法)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/metaheuristics-%E5%85%83%E5%90%AF%E5%8F%91%E5%BC%8F%E7%AE%97%E6%B3%95/">Metaheuristics (元启发式算法)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/ball_tree/Sat, 18 Jul 2026 11:08:27 +0000https://terms-en.ai-term-hub.com/zh/terms/ball_tree/<h2 id="definition">Definition</h2> <p>球树将数据点划分为嵌套的超球体（球），而不是超矩形。这种结构允许通过计算距离来进行高效的剪枝，从而加速最近邻查询。</p> <h3 id="summary">Summary</h3> <p>一种用于组织空间中点的二叉树数据结构，优化高维数据集中的最近邻搜索。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>超球体划分</li> <li>最近邻搜索</li> <li>高维数据</li> <li>树遍历</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>K近邻算法 (KNN)</li> <li>聚类分析</li> <li>异常检测</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.neighbors <span style="color:#f92672">import</span> BallTree </span></span><span style="display:flex;"><span><span style="color:#f92672">import</span> numpy <span style="color:#66d9ef">as</span> np </span></span><span style="display:flex;"><span>X <span style="color:#f92672">=</span> np<span style="color:#f92672">.</span>random<span style="color:#f92672">.</span>rand(<span style="color:#ae81ff">100</span>, <span style="color:#ae81ff">5</span>) </span></span><span style="display:flex;"><span>tree <span style="color:#f92672">=</span> BallTree(X, metric<span style="color:#f92672">=</span><span style="color:#e6db74">&#39;euclidean&#39;</span>) </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/kd-tree-k%E7%BB%B4%E6%A0%91/">KD-tree (K维树)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/k-nearest-neighbors-k%E8%BF%91%E9%82%BB/">K-Nearest Neighbors (K近邻)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/curse-of-dimensionality-%E7%BB%B4%E5%BA%A6%E7%81%BE%E9%9A%BE/">Curse of Dimensionality (维度灾难)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/automated_negotiation/Sat, 18 Jul 2026 11:08:15 +0000https://terms-en.ai-term-hub.com/zh/terms/automated_negotiation/<h2 id="definition">Definition</h2> <p>自动谈判涉及代表人类利益进行讨价还价的软件代理。这些代理利用博弈论、优化算法和机器学习来提出报价、评估对手策略并达成最优协议，常用于商业交易和资源分配场景。</p> <h3 id="summary">Summary</h3> <p>使用人工智能代理自主进行谈判并在各方之间达成协议的过程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>多智能体系统</li> <li>博弈论</li> <li>效用函数</li> <li>谈判协议</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>电子商务中的动态定价</li> <li>供应链合同管理</li> <li>云计算中的资源共享</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/multi_agent_systems-%E5%A4%9A%E6%99%BA%E8%83%BD%E4%BD%93%E7%B3%BB%E7%BB%9F/">multi_agent_systems (多智能体系统)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/game_theory-%E5%8D%9A%E5%BC%88%E8%AE%BA/">game_theory (博弈论)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/contract_net_protocol-%E5%90%88%E5%90%8C%E7%BD%91%E5%8D%8F%E8%AE%AE/">contract_net_protocol (合同网协议)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/optimization_algorithms-%E4%BC%98%E5%8C%96%E7%AE%97%E6%B3%95/">optimization_algorithms (优化算法)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/actor_critic_algorithm/Sat, 18 Jul 2026 11:04:13 +0000https://terms-en.ai-term-hub.com/zh/terms/actor_critic_algorithm/<h2 id="definition">Definition</h2> <p>演员-评论家算法包含两个组件：演员负责更新策略以选择动作，评论家则通过估计价值函数来评估这些动作的质量。两者协同工作，以提高强化学习的稳定性和效率。</p> <h3 id="summary">Summary</h3> <p>一种结合基于价值和基于策略方法的强化学习框架，使用两个神经网络：演员（Actor）和评论家（Critic）。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>策略梯度</li> <li>价值函数</li> <li>时序差分误差</li> <li>混合强化学习</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>机械臂操作</li> <li>游戏代理（如AlphaStar）</li> <li>自动驾驶中的连续控制系统</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <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/a3c-%E5%BC%82%E6%AD%A5%E4%BC%98%E5%8A%BF%E6%BC%94%E5%91%98-%E8%AF%84%E8%AE%BA%E5%AE%B6/">A3C (异步优势演员-评论家)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/policy_gradient-%E7%AD%96%E7%95%A5%E6%A2%AF%E5%BA%A6/">policy_gradient (策略梯度)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/value_function-%E4%BB%B7%E5%80%BC%E5%87%BD%E6%95%B0/">value_function (价值函数)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/unsupervised_learning/Sat, 18 Jul 2026 11:02:15 +0000https://terms-en.ai-term-hub.com/zh/terms/unsupervised_learning/<h2 id="definition">Definition</h2> <p>无监督学习自主识别原始数据中的隐藏结构、聚类或分布。常见方法包括聚类、降维和生成建模。它是</p> <h3 id="summary">Summary</h3> <p>一种机器学习技术，模型在无标签数据中学习模式，无需明确的指导或正确答案。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>聚类</li> <li>降维</li> <li>模式识别</li> <li>缺乏标注数据</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>客户细分</li> <li>异常检测</li> <li>NLP中的主题建模</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/clustering-%E8%81%9A%E7%B1%BB/">clustering (聚类)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/pca-%E4%B8%BB%E6%88%90%E5%88%86%E5%88%86%E6%9E%90/">pca (主成分分析)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/autoencoder-%E8%87%AA%E7%BC%96%E7%A0%81%E5%99%A8/">autoencoder (自编码器)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/semi_supervised_learning-%E5%8D%8A%E7%9B%91%E7%9D%A3%E5%AD%A6%E4%B9%A0/">semi_supervised_learning (半监督学习)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/optimization/Sat, 18 Jul 2026 11:01:16 +0000https://terms-en.ai-term-hub.com/zh/terms/optimization/<h2 id="definition">Definition</h2> <p>在机器学习中，优化指的是用于调整模型参数以最小化损失函数的算法，从而提高模型性能。常见方法包括梯度下降及其变体（如随机梯度下降、Adam等）。</p> <h3 id="summary">Summary</h3> <p>通过最小化或最大化目标函数来寻找最佳解决方案参数的数学过程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>损失函数最小化</li> <li>梯度下降</li> <li>学习率</li> <li>收敛</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>神经网络训练</li> <li>超参数调优</li> <li>资源分配问题</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/gradient_descent-%E6%A2%AF%E5%BA%A6%E4%B8%8B%E9%99%8D/">gradient_descent (梯度下降)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/loss_function-%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0/">loss_function (损失函数)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/backpropagation-%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD/">backpropagation (反向传播)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/hyperparameter_tuning-%E8%B6%85%E5%8F%82%E6%95%B0%E8%B0%83%E4%BC%98/">hyperparameter_tuning (超参数调优)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/one_step/Sat, 18 Jul 2026 10:57:10 +0000https://terms-en.ai-term-hub.com/zh/terms/one_step/<h2 id="definition">Definition</h2> <p>在机器学习和优化领域，一步法直接解决问题，不需要多次迭代或更新即可收敛。与需要多步才能最小化</p> <h3 id="summary">Summary</h3> <p>指在单次迭代中完成任务或决策过程，无需进行迭代优化的算法或流程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>闭式解</li> <li>计算效率</li> <li>非迭代性</li> <li>直接映射</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>通过正规方程进行的线性回归</li> <li>实时信号处理</li> <li>简单的分类规则</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/iterative-%E8%BF%AD%E4%BB%A3%E7%9A%84/">iterative (迭代的)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/gradient-descent-%E6%A2%AF%E5%BA%A6%E4%B8%8B%E9%99%8D/">gradient descent (梯度下降)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/closed-form-%E9%97%AD%E5%BC%8F%E7%9A%84/">closed-form (闭式的)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/direct-method-%E7%9B%B4%E6%8E%A5%E6%B3%95/">direct method (直接法)</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/search/Sat, 18 Jul 2026 10:54:38 +0000https://terms-en.ai-term-hub.com/zh/terms/search/<h2 id="definition">Definition</h2> <p>搜索是AI中用于导航复杂问题空间的基本范式，例如棋类游戏或路径规划。A*、极小化极大算法或蒙特卡洛树搜索等算法评估潜在的</p> <h3 id="summary">Summary</h3> <p>搜索算法系统地探索解空间，以在AI任务中寻找最优或令人满意的结果。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>状态空间</li> <li>启发式方法</li> <li>优化</li> <li>路径查找</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>游戏AI策略</li> <li>机器人路径规划</li> <li>约束满足问题</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/algorithm-%E7%AE%97%E6%B3%95/">Algorithm (算法)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/heuristic-%E5%90%AF%E5%8F%91%E5%BC%8F/">Heuristic (启发式)</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> <li><a href="https://terms-en.ai-term-hub.com/en/terms/planning-%E8%A7%84%E5%88%92/">Planning (规划)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/reinforcement_learning/Sat, 18 Jul 2026 10:54:14 +0000https://terms-en.ai-term-hub.com/zh/terms/reinforcement_learning/<h2 id="definition">Definition</h2> <p>强化学习（RL）是机器学习的一个分支，专注于智能体应如何在环境中采取行动以最大化累积奖励的概念。与监督学习不同，强化学习不依赖标记数据，而是通过试错和奖励信号进行学习。</p> <h3 id="summary">Summary</h3> <p>强化学习是机器学习的一种类型，智能体通过与环境交互并最大化奖励来学习做出决策。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>智能体（Agent）</li> <li>环境</li> <li>策略</li> <li>奖励函数</li> <li>状态空间</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>自动驾驶</li> <li>游戏AI（如AlphaGo）</li> <li>推荐系统</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/deep-q-networks-%E6%B7%B1%E5%BA%A6q%E7%BD%91%E7%BB%9C/">Deep Q-Networks（深度Q网络）</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/policy-gradient-%E7%AD%96%E7%95%A5%E6%A2%AF%E5%BA%A6/">Policy Gradient（策略梯度）</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/markov-decision-process-%E9%A9%AC%E5%B0%94%E5%8F%AF%E5%A4%AB%E5%86%B3%E7%AD%96%E8%BF%87%E7%A8%8B/">Markov Decision Process（马尔可夫决策过程）</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/matching/Sat, 18 Jul 2026 10:53:03 +0000https://terms-en.ai-term-hub.com/zh/terms/matching/<h2 id="definition">Definition</h2> <p>匹配是机器学习中用于建立不同数据实体之间关系的关键技术。在计算机视觉中，特征匹配用于识别图像间的对应点；在推荐系统中，则用于匹配用户偏好与物品特征。</p> <h3 id="summary">Summary</h3> <p>匹配涉及将两组数据点或特征对齐，以识别它们之间的对应关系、相似性或最优配对。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>特征对应</li> <li>相似度度量</li> <li>嵌入空间</li> <li>最近邻搜索</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>视频中的目标跟踪</li> <li>推荐引擎</li> <li>数据库中的重复项检测</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/cosine-similarity-%E4%BD%99%E5%BC%A6%E7%9B%B8%E4%BC%BC%E5%BA%A6/">Cosine Similarity (余弦相似度)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/retrieval-%E6%A3%80%E7%B4%A2/">Retrieval (检索)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/clustering-%E8%81%9A%E7%B1%BB/">Clustering (聚类)</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> </ul>https://terms-en.ai-term-hub.com/zh/terms/decision/Sat, 18 Jul 2026 10:49:53 +0000https://terms-en.ai-term-hub.com/zh/terms/decision/<h2 id="definition">Definition</h2> <p>AI中的决策制定涉及基于数据、模型和预定义目标从一组可能性中选择最佳行动。它可以是确定性的，遵循严格规则，也可以是概率性的，处理不确定性。</p> <h3 id="summary">Summary</h3> <p>智能体或算法在根据特定标准或目标评估可用选项后做出的选择。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>优化</li> <li>不确定性</li> <li>策略</li> <li>评估</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>医疗诊断支持</li> <li>信用评分系统</li> <li>游戏策略</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/classification-%E5%88%86%E7%B1%BB/">Classification (分类)</a></li> <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/bayesian-inference-%E8%B4%9D%E5%8F%B6%E6%96%AF%E6%8E%A8%E6%96%AD/">Bayesian Inference (贝叶斯推断)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/carlo/Sat, 18 Jul 2026 10:49:30 +0000https://terms-en.ai-term-hub.com/zh/terms/carlo/<h2 id="definition">Definition</h2> <p>蒙特卡洛方法是AI和统计学中用于近似难以解析求解的复杂数学问题的关键技术。通过生成成千上万个随机样本来估算结果。</p> <h3 id="summary">Summary</h3> <p>指蒙特卡洛方法，这是一类依赖重复随机采样以获得数值结果的计算算法。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>随机采样</li> <li>统计近似</li> <li>模拟</li> <li>概率估计</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>通过模拟估计强化学习中的状态值。</li> <li>使用马尔可夫链蒙特卡洛（MCMC）进行贝叶斯后验推断。</li> <li>为高维空间中的概率模型计算积分。</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">import</span> numpy <span style="color:#66d9ef">as</span> np </span></span><span style="display:flex;"><span><span style="color:#75715e"># Monte Carlo estimation of Pi</span> </span></span><span style="display:flex;"><span><span style="color:#66d9ef">def</span> <span style="color:#a6e22e">estimate_pi</span>(samples): </span></span><span style="display:flex;"><span> points <span style="color:#f92672">=</span> np<span style="color:#f92672">.</span>random<span style="color:#f92672">.</span>uniform(<span style="color:#f92672">-</span><span style="color:#ae81ff">1</span>, <span style="color:#ae81ff">1</span>, size<span style="color:#f92672">=</span>(samples, <span style="color:#ae81ff">2</span>)) </span></span><span style="display:flex;"><span> inside <span style="color:#f92672">=</span> np<span style="color:#f92672">.</span>sum(points[:, <span style="color:#ae81ff">0</span>]<span style="color:#f92672">**</span><span style="color:#ae81ff">2</span> <span style="color:#f92672">+</span> points[:, <span style="color:#ae81ff">1</span>]<span style="color:#f92672">**</span><span style="color:#ae81ff">2</span> <span style="color:#f92672">&lt;=</span> <span style="color:#ae81ff">1</span>) </span></span><span style="display:flex;"><span> <span style="color:#66d9ef">return</span> <span style="color:#ae81ff">4</span> <span style="color:#f92672">*</span> inside <span style="color:#f92672">/</span> samples </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/monte_carlo-%E8%92%99%E7%89%B9%E5%8D%A1%E6%B4%9B/">Monte_Carlo (蒙特卡洛)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/simulation-%E6%A8%A1%E6%8B%9F/">simulation (模拟)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/random_sampling-%E9%9A%8F%E6%9C%BA%E9%87%87%E6%A0%B7/">random_sampling (随机采样)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/mcmc-%E9%A9%AC%E5%B0%94%E5%8F%AF%E5%A4%AB%E9%93%BE%E8%92%99%E7%89%B9%E5%8D%A1%E6%B4%9B/">MCMC (马尔可夫链蒙特卡洛)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/adam/Sat, 18 Jul 2026 10:49:06 +0000https://terms-en.ai-term-hub.com/zh/terms/adam/<h2 id="definition">Definition</h2> <p>Adam（自适应矩估计）是一种流行的基于一阶梯度的优化算法，用于训练深度神经网络。它结合了两种其他随机梯度下降扩展的优势。</p> <h3 id="summary">Summary</h3> <p>一种为每个参数计算自适应学习率的优化算法。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>梯度下降</li> <li>学习率</li> <li>动量</li> <li>方差估计</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>深度学习训练</li> <li>计算机视觉模型</li> <li>自然语言处理</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">import</span> torch.optim <span style="color:#66d9ef">as</span> optim </span></span><span style="display:flex;"><span>optimizer <span style="color:#f92672">=</span> optim<span style="color:#f92672">.</span>Adam(model<span style="color:#f92672">.</span>parameters(), lr<span style="color:#f92672">=</span><span style="color:#ae81ff">0.001</span>) </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/sgd-%E9%9A%8F%E6%9C%BA%E6%A2%AF%E5%BA%A6%E4%B8%8B%E9%99%8D/">SGD (随机梯度下降)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/rmsprop-%E5%9D%87%E6%96%B9%E6%A0%B9%E4%BC%A0%E6%92%AD/">RMSProp (均方根传播)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/optimizer-%E4%BC%98%E5%8C%96%E5%99%A8/">Optimizer (优化器)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/backpropagation-%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD/">Backpropagation (反向传播)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/backpropagation/Sat, 18 Jul 2026 07:44:10 +0000https://terms-en.ai-term-hub.com/zh/terms/backpropagation/<h2 id="definition">Definition</h2> <p>反向传播（Backpropagation），即误差反向传播，是一种用于人工神经网络的方法，旨在计算损失函数关于权重的梯度。它通过将误差信号从输出层向输入层反向传播，并利用链式法则更新权重，从而优化模型性能。</p> <h3 id="summary">Summary</h3> <p>一种广泛用于训练神经网络的算法，通过计算梯度来最小化误差。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>梯度下降</li> <li>链式法则</li> <li>损失函数</li> <li>权重更新</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>深度神经网络训练</li> <li>图像分类任务</li> <li>语音识别系统</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/gradient-descent-%E6%A2%AF%E5%BA%A6%E4%B8%8B%E9%99%8D/">Gradient Descent (梯度下降)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/neural-network-%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C/">Neural Network (神经网络)</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>