https://terms-en.ai-term-hub.com/zh/tags/technique/Recent content in Technique 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/self_consistency/Sat, 18 Jul 2026 11:32:54 +0000https://terms-en.ai-term-hub.com/zh/terms/self_consistency/<h2 id="definition">Definition</h2> <p>该技术主要用于大型语言模型（LLM），通过采样生成针对同一提示的多个多样化响应来提高准确性。与依赖贪婪解码不同，它聚合</p> <h3 id="summary">Summary</h3> <p>自洽性是一种解码策略，其中采样多个推理路径，并选择出现频率最高的答案作为最终输出。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>多数投票</li> <li>解码策略</li> <li>LLM推理</li> <li>减少幻觉</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>数学应用题</li> <li>复杂逻辑推导</li> <li>代码合成任务</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%80%9D%E7%BB%B4%E9%93%BE-chain-of-thought-%E5%BC%95%E5%AF%BC%E6%A8%A1%E5%9E%8B%E9%80%90%E6%AD%A5%E6%8E%A8%E7%90%86%E7%9A%84%E6%8A%80%E6%9C%AF/">思维链 (Chain-of-thought，引导模型逐步推理的技术)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%B8%A9%E5%BA%A6%E9%87%87%E6%A0%B7-temperature-sampling-%E6%8E%A7%E5%88%B6%E7%94%9F%E6%88%90%E6%96%87%E6%9C%AC%E9%9A%8F%E6%9C%BA%E6%80%A7%E7%9A%84%E5%8F%82%E6%95%B0/">温度采样 (Temperature sampling，控制生成文本随机性的参数)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E9%9B%86%E6%88%90%E6%96%B9%E6%B3%95-ensemble-methods-%E7%BB%93%E5%90%88%E5%A4%9A%E4%B8%AA%E6%A8%A1%E5%9E%8B%E9%A2%84%E6%B5%8B%E4%BB%A5%E6%8F%90%E9%AB%98%E5%87%86%E7%A1%AE%E6%80%A7%E7%9A%84%E6%8A%80%E6%9C%AF/">集成方法 (Ensemble methods，结合多个模型预测以提高准确性的技术)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%8F%90%E7%A4%BA%E5%B7%A5%E7%A8%8B-prompt-engineering-%E8%AE%BE%E8%AE%A1%E5%92%8C%E4%BC%98%E5%8C%96%E8%BE%93%E5%85%A5%E6%8F%90%E7%A4%BA%E4%BB%A5%E6%94%B9%E5%96%84%E6%A8%A1%E5%9E%8B%E8%BE%93%E5%87%BA%E7%9A%84%E6%8A%80%E6%9C%AF/">提示工程 (Prompt engineering，设计和优化输入提示以改善模型输出的技术)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/feature_engineering/Sat, 18 Jul 2026 11:17:01 +0000https://terms-en.ai-term-hub.com/zh/terms/feature_engineering/<h2 id="definition">Definition</h2> <p>特征工程是利用领域专业知识，将原始数据转换为更能代表底层模式的特征的艺术。该过程包括创建新变量、转换现有数据以及选择最具预测力的特征，从而提升算法效果。</p> <h3 id="summary">Summary</h3> <p>利用领域知识创建新特征或修改现有特征，以增强机器学习模型性能的做法。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>领域知识</li> <li>数据转换</li> <li>模型性能</li> <li>变量创建</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>提高回归模型准确性</li> <li>增强分类边界</li> <li>优化时间序列预测</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>df[<span style="color:#e6db74">&#39;new_feature&#39;</span>] <span style="color:#f92672">=</span> df[<span style="color:#e6db74">&#39;feature_a&#39;</span>] <span style="color:#f92672">*</span> df[<span style="color:#e6db74">&#39;feature_b&#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/%E7%89%B9%E5%BE%81%E6%8F%90%E5%8F%96/">特征提取</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%95%B0%E6%8D%AE%E9%A2%84%E5%A4%84%E7%90%86/">数据预处理</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%A8%A1%E5%9E%8B%E8%B0%83%E4%BC%98/">模型调优</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E9%A2%86%E5%9F%9F%E4%B8%93%E9%95%BF/">领域专长</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/feature_extraction/Sat, 18 Jul 2026 11:17:01 +0000https://terms-en.ai-term-hub.com/zh/terms/feature_extraction/<h2 id="definition">Definition</h2> <p>特征提取涉及将原始数据转换为一组更能代表潜在问题的特征，从而提高预测模型的准确性。该技术有助于减少数据维度并增强模型表现。</p> <h3 id="summary">Summary</h3> <p>从原始数据中推导有意义信息的过程，旨在降低维度并提高机器学习模型的性能。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>降维</li> <li>原始数据转换</li> <li>模式识别</li> <li>主成分</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>图像识别任务</li> <li>自然语言处理</li> <li>音频信号处理</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">from</span> sklearn.decomposition <span style="color:#f92672">import</span> PCA </span></span><span style="display:flex;"><span>pca <span style="color:#f92672">=</span> PCA(n_components<span style="color:#f92672">=</span><span style="color:#ae81ff">2</span>) </span></span><span style="display:flex;"><span>reduced_data <span style="color:#f92672">=</span> pca<span style="color:#f92672">.</span>fit_transform(raw_data) </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/pca/">PCA</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%B5%8C%E5%85%A5/">嵌入</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E7%89%B9%E5%BE%81%E9%80%89%E6%8B%A9/">特征选择</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/">深度学习</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/few_shot_prompting/Sat, 18 Jul 2026 11:00:03 +0000https://terms-en.ai-term-hub.com/zh/terms/few_shot_prompting/<h2 id="definition">Definition</h2> <p>这种方法利用大型语言模型的上下文学习能力，直接在提示词中提供几个说明性示例。与需要更新模型权重的微调不同，少样本提示通过展示期望的输出格式或逻辑，让模型在不重新训练的情况下适应新任务。</p> <h3 id="summary">Summary</h3> <p>少样本提示是一种技术，通过在提示词中提供少量输入-输出示例来引导大型语言模型的行为。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>上下文学习</li> <li>提示工程</li> <li>基于示例的引导</li> <li>零样本对比</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>情感分析格式化</li> <li>代码风格适配</li> <li>结构化数据提取</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>response <span style="color:#f92672">=</span> llm<span style="color:#f92672">.</span>generate( </span></span><span style="display:flex;"><span> prompt<span style="color:#f92672">=</span><span style="color:#e6db74">&#34;Translate English to French:</span><span style="color:#ae81ff">\n</span><span style="color:#e6db74">&#34;</span> </span></span><span style="display:flex;"><span> <span style="color:#e6db74">&#34;Hello -&gt; Bonjour</span><span style="color:#ae81ff">\n</span><span style="color:#e6db74">&#34;</span> </span></span><span style="display:flex;"><span> <span style="color:#e6db74">&#34;World -&gt; Monde</span><span style="color:#ae81ff">\n</span><span style="color:#e6db74">&#34;</span> </span></span><span style="display:flex;"><span> <span style="color:#e6db74">&#34;Cat -&gt; ?&#34;</span> </span></span><span style="display:flex;"><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/zero_shot-%E9%9B%B6%E6%A0%B7%E6%9C%AC/">zero_shot (零样本)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/prompt_engineering-%E6%8F%90%E7%A4%BA%E5%B7%A5%E7%A8%8B/">prompt_engineering (提示工程)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/in_context_learning-%E4%B8%8A%E4%B8%8B%E6%96%87%E5%AD%A6%E4%B9%A0/">in_context_learning (上下文学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/llm-%E5%A4%A7%E5%9E%8B%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B/">llm (大型语言模型)</a></li> </ul>