Fundamentals on 中文AI术语词典https://terms-en.ai-term-hub.com/zh/tags/fundamentals/Recent content in Fundamentals on 中文AI术语词典Hugozh-cnSat, 18 Jul 2026 11:44:45 +0000弱人工智能https://terms-en.ai-term-hub.com/zh/terms/weak_artificial_intelligence/Sat, 18 Jul 2026 11:38:02 +0000https://terms-en.ai-term-hub.com/zh/terms/weak_artificial_intelligence/<h2 id="definition">Definition</h2> <p>弱人工智能，也称为狭义AI，是指为解决特定问题或执行特定任务（如面部识别或语言翻译）而构建的系统。与强人工智能不同，它不具备通用的智能或意识。</p> <h3 id="summary">Summary</h3> <p>专为在有限范围内执行特定任务而设计的AI，不具备通用认知能力。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>狭窄的范围</li> <li>针对特定任务的优化</li> <li>无意识</li> <li>有限的推理能力</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>推荐引擎</li> <li>自动驾驶感知系统</li> <li>自然语言处理聊天机器人</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/strong-artificial-intelligence-%E5%BC%BA%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/">Strong artificial intelligence (强人工智能)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/artificial-general-intelligence-%E4%BA%BA%E5%B7%A5%E9%80%9A%E7%94%A8%E6%99%BA%E8%83%BD/">Artificial General Intelligence (人工通用智能)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/machine-learning-%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/">Machine Learning (机器学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/narrow-ai-%E7%8B%AD%E4%B9%89ai/">Narrow AI (狭义AI)</a></li> </ul>量化https://terms-en.ai-term-hub.com/zh/terms/quantification/Sat, 18 Jul 2026 11:31:12 +0000https://terms-en.ai-term-hub.com/zh/terms/quantification/<h2 id="definition">Definition</h2> <p>在人工智能和数据科学的背景下，量化指的是将非数值数据（如文本、图像或主观意见）转换为可测量的数值的过程。这一过程使计算机能够处理和理解原本难以量化的信息。</p> <h3 id="summary">Summary</h3> <p>量化是将定性属性或抽象概念以数值形式表达以便进行分析的过程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>数值表示</li> <li>特征工程</li> <li>数据转换</li> <li>测量</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>自然语言处理 (NLP)</li> <li>情感评分</li> <li>图像像素值分析</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E7%BC%96%E7%A0%81-encoding/">编码 (Encoding)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%BD%92%E4%B8%80%E5%8C%96-normalization/">归一化 (Normalization)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%90%91%E9%87%8F%E5%8C%96-vectorization/">向量化 (Vectorization)</a></li> </ul>机器学习概述https://terms-en.ai-term-hub.com/zh/terms/outline_of_machine_learning/Sat, 18 Jul 2026 11:29:02 +0000https://terms-en.ai-term-hub.com/zh/terms/outline_of_machine_learning/<h2 id="definition">Definition</h2> <p>该术语描述了机器学习的结构化分类，分为监督学习、无监督学习、半监督学习和强化学习。它包括核心算法族，如线性回归、决策树和支持向量机，并涵盖模型评估的关键指标。</p> <h3 id="summary">Summary</h3> <p>对机器学习范式、算法和评估指标的综合分类。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>监督学习</li> <li>无监督学习</li> <li>强化学习</li> <li>模型评估</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>算法选择指南</li> <li>数据科学工作流规划</li> <li>学术分类体系构建</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0-deep-learning/">深度学习 (Deep Learning)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E7%BB%9F%E8%AE%A1%E5%AD%A6%E4%B9%A0-statistical-learning/">统计学习 (Statistical Learning)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E7%89%B9%E5%BE%81%E5%B7%A5%E7%A8%8B-feature-engineering/">特征工程 (Feature Engineering)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E4%BA%A4%E5%8F%89%E9%AA%8C%E8%AF%81-cross-validation/">交叉验证 (Cross-Validation)</a></li> </ul>深度学习概述https://terms-en.ai-term-hub.com/zh/terms/outline_of_deep_learning/Sat, 18 Jul 2026 11:29:02 +0000https://terms-en.ai-term-hub.com/zh/terms/outline_of_deep_learning/<h2 id="definition">Definition</h2> <p>深度学习概述涵盖了基本结构，如神经网络层、激活函数和损失度量。它详细说明了训练技术，包括反向传播、梯度下降以及特征提取等关键概念，为理解复杂模型提供了基础框架。</p> <h3 id="summary">Summary</h3> <p>对深度学习方法论、架构和优化策略的结构化概览。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>神经网络架构</li> <li>反向传播</li> <li>优化算法</li> <li>特征提取</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>AI教育课程设计</li> <li>模型架构选择</li> <li>超参数调优策略</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0-machine-learning/">机器学习 (Machine Learning)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C-convolutional-neural-networks/">卷积神经网络 (Convolutional Neural Networks)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%A2%AF%E5%BA%A6%E4%B8%8B%E9%99%8D-gradient-descent/">梯度下降 (Gradient Descent)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E8%BF%87%E6%8B%9F%E5%90%88-overfitting/">过拟合 (Overfitting)</a></li> </ul>神经计算https://terms-en.ai-term-hub.com/zh/terms/neural_computation/Sat, 18 Jul 2026 11:28:12 +0000https://terms-en.ai-term-hub.com/zh/terms/neural_computation/<h2 id="definition">Definition</h2> <p>神经计算是指人工神经元执行数学运算，将输入信号转化为输出响应的过程。它涉及加权求和、激活函数以及反向传播（backpropagation）。</p> <h3 id="summary">Summary</h3> <p>受生物神经元启发的神经网络中信息处理的过程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>激活函数</li> <li>加权求和</li> <li>反向传播</li> <li>分布式表示</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>图像识别系统</li> <li>自然语言处理模型</li> <li>预测性分析</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/deep-learning-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/">Deep learning (深度学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/perceptron-%E6%84%9F%E7%9F%A5%E6%9C%BA/">Perceptron (感知机)</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/synaptic-weight-%E7%AA%81%E8%A7%A6%E6%9D%83%E9%87%8D/">Synaptic weight (突触权重)</a></li> </ul>标注数据https://terms-en.ai-term-hub.com/zh/terms/labeled_data/Sat, 18 Jul 2026 11:23:41 +0000https://terms-en.ai-term-hub.com/zh/terms/labeled_data/<h2 id="definition">Definition</h2> <p>标注数据由输入样本及其对应的真实标签组成，是监督机器学习的基础。它允许算法学习输入与输出之间的映射关系。</p> <h3 id="summary">Summary</h3> <p>在输入特征旁边提供正确输出或目标值的数据。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>监督学习</li> <li>真实标签</li> <li>标注</li> <li>目标变量</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>训练图像分类器</li> <li>构建语音识别系统</li> <li>金融领域的预测建模</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> pandas <span style="color:#66d9ef">as</span> pd </span></span><span style="display:flex;"><span><span style="color:#75715e"># Example of loading labeled data</span> </span></span><span style="display:flex;"><span>df <span style="color:#f92672">=</span> pd<span style="color:#f92672">.</span>read_csv(<span style="color:#e6db74">&#39;train.csv&#39;</span>) </span></span><span style="display:flex;"><span>X <span style="color:#f92672">=</span> df<span style="color:#f92672">.</span>drop(<span style="color:#e6db74">&#39;label&#39;</span>, axis<span style="color:#f92672">=</span><span style="color:#ae81ff">1</span>) </span></span><span style="display:flex;"><span>y <span style="color:#f92672">=</span> df[<span style="color:#e6db74">&#39;label&#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/unlabeled_data-%E6%9C%AA%E6%A0%87%E6%B3%A8%E6%95%B0%E6%8D%AE/">unlabeled_data (未标注数据)</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/data_annotation-%E6%95%B0%E6%8D%AE%E6%A0%87%E6%B3%A8/">data_annotation (数据标注)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/training_set-%E8%AE%AD%E7%BB%83%E9%9B%86/">training_set (训练集)</a></li> </ul>前馈网络https://terms-en.ai-term-hub.com/zh/terms/feed_forward_network/Sat, 18 Jul 2026 11:17:13 +0000https://terms-en.ai-term-hub.com/zh/terms/feed_forward_network/<h2 id="definition">Definition</h2> <p>前馈网络（FFN），也称为多层感知机（MLP），通过从输入层到输出层的神经元层顺序处理数据，没有反馈回路。每个神经元接收输入信号的加权总和，并通过激活函数进行处理，将结果传递给下一层。这种架构是许多深度学习模型的基础组件。</p> <h3 id="summary">Summary</h3> <p>一类人工神经网络，节点间的连接不形成循环，信息沿单一方向传播。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>无循环</li> <li>层级（输入、隐藏、输出）</li> <li>激活函数</li> <li>加权和</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>简单回归任务</li> <li>表格数据的分类问题</li> <li>构建更深层次架构的基础模块</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.nn <span style="color:#66d9ef">as</span> nn </span></span><span style="display:flex;"><span> </span></span><span style="display:flex;"><span><span style="color:#66d9ef">class</span> <span style="color:#a6e22e">SimpleFFN</span>(nn<span style="color:#f92672">.</span>Module): </span></span><span style="display:flex;"><span> <span style="color:#66d9ef">def</span> __init__(self, input_size, hidden_size, output_size): </span></span><span style="display:flex;"><span> super(SimpleFFN, self)<span style="color:#f92672">.</span>__init__() </span></span><span style="display:flex;"><span> self<span style="color:#f92672">.</span>fc1 <span style="color:#f92672">=</span> nn<span style="color:#f92672">.</span>Linear(input_size, hidden_size) </span></span><span style="display:flex;"><span> self<span style="color:#f92672">.</span>relu <span style="color:#f92672">=</span> nn<span style="color:#f92672">.</span>ReLU() </span></span><span style="display:flex;"><span> self<span style="color:#f92672">.</span>fc2 <span style="color:#f92672">=</span> nn<span style="color:#f92672">.</span>Linear(hidden_size, output_size) </span></span><span style="display:flex;"><span> </span></span><span style="display:flex;"><span> <span style="color:#66d9ef">def</span> <span style="color:#a6e22e">forward</span>(self, x): </span></span><span style="display:flex;"><span> x <span style="color:#f92672">=</span> self<span style="color:#f92672">.</span>fc1(x) </span></span><span style="display:flex;"><span> x <span style="color:#f92672">=</span> self<span style="color:#f92672">.</span>relu(x) </span></span><span style="display:flex;"><span> x <span style="color:#f92672">=</span> self<span style="color:#f92672">.</span>fc2(x) </span></span><span style="display:flex;"><span> <span style="color:#66d9ef">return</span> x </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/multi-layer-perceptron-%E5%A4%9A%E5%B1%82%E6%84%9F%E7%9F%A5%E6%9C%BA/">Multi-Layer Perceptron (多层感知机)</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/activation-function-%E6%BF%80%E6%B4%BB%E5%87%BD%E6%95%B0/">Activation Function (激活函数)</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> </ul>编码https://terms-en.ai-term-hub.com/zh/terms/coding/Sat, 18 Jul 2026 11:10:26 +0000https://terms-en.ai-term-hub.com/zh/terms/coding/<h2 id="definition">Definition</h2> <p>编码，也称为编程，涉及将人类逻辑和需求转换为计算机可执行的格式。它使用特定编程语言定义的语法和语义&hellip;</p> <h3 id="summary">Summary</h3> <p>编码是使用编程语言编写计算机指令以创建软件、应用程序或脚本的过程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>编程语言</li> <li>语法</li> <li>算法</li> <li>软件开发</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>构建 Web 应用程序</li> <li>创建移动应用</li> <li>开发人工智能模型</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>print(<span style="color:#e6db74">&#34;Hello, World!&#34;</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/programming-%E7%BC%96%E7%A8%8B/">Programming (编程)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/scripting-%E8%84%9A%E6%9C%AC%E7%BC%96%E5%86%99/">Scripting (脚本编写)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/debugging-%E8%B0%83%E8%AF%95/">Debugging (调试)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/ide-%E9%9B%86%E6%88%90%E5%BC%80%E5%8F%91%E7%8E%AF%E5%A2%83/">IDE (集成开发环境)</a></li> </ul>聊天https://terms-en.ai-term-hub.com/zh/terms/chat/Sat, 18 Jul 2026 11:09:54 +0000https://terms-en.ai-term-hub.com/zh/terms/chat/<h2 id="definition">Definition</h2> <p>在AI语境下，聊天指实时、轮流对话的界面和底层机制。它允许用户提问、请求执行任务或进行开放式对话。</p> <h3 id="summary">Summary</h3> <p>聊天指用户与AI系统之间通过自然语言进行的交互式对话通信。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>自然语言接口</li> <li>上下文窗口</li> <li>对话管理</li> <li>用户交互</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>客户服务机器人</li> <li>个人助手</li> <li>教育辅导系统</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/llm-%E5%A4%A7%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B/">LLM (大语言模型)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/conversational-ai-%E5%AF%B9%E8%AF%9D%E5%BC%8F%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/">Conversational AI (对话式人工智能)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/prompt-%E6%8F%90%E7%A4%BA%E8%AF%8D/">Prompt (提示词)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/dialogue-%E5%AF%B9%E8%AF%9D/">Dialogue (对话)</a></li> </ul>字符计算https://terms-en.ai-term-hub.com/zh/terms/character_computing/Sat, 18 Jul 2026 11:09:54 +0000https://terms-en.ai-term-hub.com/zh/terms/character_computing/<h2 id="definition">Definition</h2> <p>这一概念侧重于文本操作，其中计算的基本单位是单个字符。它通常用于需要细粒度文本分析的任务，例如拼写检查。</p> <h3 id="summary">Summary</h3> <p>字符计算涉及在单个字符层面而非单词或句子层面处理、生成或分析文本。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>分词</li> <li>文本生成</li> <li>细粒度分析</li> <li>子词单元</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>手写识别（OCR）</li> <li>低资源语言建模</li> <li>密文分析</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/token-%E8%AF%8D%E5%85%83/">Token (词元)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/nlp-%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/">NLP (自然语言处理)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/rnn-%E5%BE%AA%E7%8E%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C/">RNN (循环神经网络)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/transformer-%E5%8F%98%E6%8D%A2%E5%99%A8%E6%9E%B6%E6%9E%84/">Transformer (变换器架构)</a></li> </ul>代码https://terms-en.ai-term-hub.com/zh/terms/code/Sat, 18 Jul 2026 10:59:27 +0000https://terms-en.ai-term-hub.com/zh/terms/code/<h2 id="definition">Definition</h2> <p>代码是用Python、C++或JavaScript等编程语言编写的一组指令，计算机执行这些指令以执行特定任务。在人工智能中，代码是构建神经网络、实现算法以及部署模型服务的基础。它将抽象的AI概念转化为可执行的计算步骤。</p> <h3 id="summary">Summary</h3> <p>在AI语境中，代码指用编程语言编写的结构化指令，用于定义模型行为和数据处理的逻辑。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>编程语言</li> <li>软件实现</li> <li>算法执行</li> <li>开发</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>构建神经网络层</li> <li>创建数据预处理脚本</li> <li>部署模型的API端点</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:#66d9ef">def</span> <span style="color:#a6e22e">add</span>(a, b): </span></span><span style="display:flex;"><span> <span style="color:#66d9ef">return</span> a <span style="color:#f92672">+</span> b </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/python-python%E7%BC%96%E7%A8%8B%E8%AF%AD%E8%A8%80/">Python (Python编程语言)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/source-code-%E6%BA%90%E4%BB%A3%E7%A0%81/">Source Code (源代码)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/software-development-%E8%BD%AF%E4%BB%B6%E5%BC%80%E5%8F%91/">Software Development (软件开发)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/implementation-%E5%AE%9E%E7%8E%B0/">Implementation (实现)</a></li> </ul>权衡https://terms-en.ai-term-hub.com/zh/terms/trade_off/Sat, 18 Jul 2026 10:59:01 +0000https://terms-en.ai-term-hub.com/zh/terms/trade_off/<h2 id="definition">Definition</h2> <p>在人工智能和工程领域，权衡指的是在优化相互冲突的目标（如模型准确率与计算成本，或延迟与精度）时所需的平衡。由于资源有限，必须在不同指标之间做出取舍。</p> <h3 id="summary">Summary</h3> <p>一种妥协，即在某一领域获得优势的同时，在另一领域遭受损失。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>资源分配</li> <li>优化</li> <li>准确率与速度的权衡</li> <li>偏差-方差权衡</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>为边缘设备选择模型大小</li> <li>平衡推理延迟与预测准确率</li> <li>训练期间管理内存使用量</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <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/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> <li><a href="https://terms-en.ai-term-hub.com/en/terms/model_compression-%E6%A8%A1%E5%9E%8B%E5%8E%8B%E7%BC%A9/">model_compression (模型压缩)</a></li> </ul>词元https://terms-en.ai-term-hub.com/zh/terms/token/Sat, 18 Jul 2026 10:55:25 +0000https://terms-en.ai-term-hub.com/zh/terms/token/<h2 id="definition">Definition</h2> <h3 id="summary">Summary</h3> <p>词元是文本或数据的离散单元，作为自然语言处理模型的基本输入元素。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>离散单元</li> <li>词汇表</li> <li>嵌入</li> <li>上下文窗口</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>LLM中的文本生成</li> <li>机器翻译预处理</li> <li>情感分析输入格式化</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/tokenization-%E5%88%86%E8%AF%8D/">Tokenization (分词)</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/vocabulary-%E8%AF%8D%E6%B1%87%E8%A1%A8/">Vocabulary (词汇表)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/subword-%E5%AD%90%E8%AF%8D/">Subword (子词)</a></li> </ul>时间https://terms-en.ai-term-hub.com/zh/terms/time/Sat, 18 Jul 2026 10:55:25 +0000https://terms-en.ai-term-hub.com/zh/terms/time/<h2 id="definition">Definition</h2> <p>时间是人工智能中的一个基本概念，尤其在序列建模和实时系统中至关重要。它作为数据点排序的轴，使循环神经网络（RNN）等模型能够处理依赖时间顺序的数据。</p> <h3 id="summary">Summary</h3> <p>在人工智能中，时间指用于对事件进行排序、跟踪状态变化以及衡量模型操作延迟或持续时间的时序维度。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>时序排序</li> <li>延迟</li> <li>状态跟踪</li> <li>因果关系</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>基于随时间变化的传感器数据进行预测性维护</li> <li>实时语音识别</li> <li>股票市场趋势分析</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/sequence-%E5%BA%8F%E5%88%97/">Sequence (序列)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/latency-%E5%BB%B6%E8%BF%9F/">Latency (延迟)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/timestamp-%E6%97%B6%E9%97%B4%E6%88%B3/">Timestamp (时间戳)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/temporal-%E6%97%B6%E5%BA%8F%E7%9A%84/">Temporal (时序的)</a></li> </ul>规模https://terms-en.ai-term-hub.com/zh/terms/scale/Sat, 18 Jul 2026 10:54:38 +0000https://terms-en.ai-term-hub.com/zh/terms/scale/<h2 id="definition">Definition</h2> <p>在人工智能领域，扩展通常涉及增加数据集大小、模型参数或计算能力以提升性能。这一概念在深度学习中至关重要，其中大规模</p> <h3 id="summary">Summary</h3> <p>规模指机器学习模型中使用的数据量、参数量或计算资源的大小。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>模型参数</li> <li>数据集大小</li> <li>计算能力</li> <li>缩放定律</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>训练大型语言模型</li> <li>优化神经网络容量</li> <li>AI基础设施的资源规划</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/scaling-%E7%BC%A9%E6%94%BE-%E6%89%A9%E5%B1%95/">Scaling (缩放/扩展)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/big-data-%E5%A4%A7%E6%95%B0%E6%8D%AE/">Big Data (大数据)</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> <li><a href="https://terms-en.ai-term-hub.com/en/terms/compute-%E8%AE%A1%E7%AE%97/">Compute (计算)</a></li> </ul>流程https://terms-en.ai-term-hub.com/zh/terms/process/Sat, 18 Jul 2026 10:54:02 +0000https://terms-en.ai-term-hub.com/zh/terms/process/<h2 id="definition">Definition</h2> <p>在AI开发中，流程指将原始数据转化为可操作见解或模型所需的系统化工作流。这包括数据摄取、预处理、特征……等阶段。</p> <h3 id="summary">Summary</h3> <p>为实现特定计算目标或结果而采取的结构化行动或步骤系列。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>管道 (Pipeline)</li> <li>工作流 (Workflow)</li> <li>自动化 (Automation)</li> <li>迭代 (Iteration)</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>端到端MLOps管道</li> <li>数据清洗程序</li> <li>模型重训练计划</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/pipeline-%E7%AE%A1%E9%81%93/">Pipeline (管道)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/workflow-%E5%B7%A5%E4%BD%9C%E6%B5%81/">Workflow (工作流)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/system-%E7%B3%BB%E7%BB%9F/">System (系统)</a></li> </ul>随机https://terms-en.ai-term-hub.com/zh/terms/random/Sat, 18 Jul 2026 10:54:02 +0000https://terms-en.ai-term-hub.com/zh/terms/random/<h2 id="definition">Definition</h2> <p>随机性是AI的基础，用于初始化模型权重、打乱数据集以及在训练过程中引入随机性以防止过拟合。由于计算机是确定性的，AI系统……</p> <h3 id="summary">Summary</h3> <p>缺乏可预测模式的属性，通常在AI中通过伪随机数生成算法来模拟。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>种子值</li> <li>随机性</li> <li>伪随机</li> <li>可复现性</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>神经网络中的权重初始化</li> <li>Dropout正则化</li> <li>强化学习中的探索</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>np<span style="color:#f92672">.</span>random<span style="color:#f92672">.</span>seed(<span style="color:#ae81ff">42</span>) </span></span><span style="display:flex;"><span>print(np<span style="color:#f92672">.</span>random<span style="color:#f92672">.</span>rand()) </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/noise-%E5%99%AA%E5%A3%B0/">Noise (噪声)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/entropy-%E7%86%B5/">Entropy (熵)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/distribution-%E5%88%86%E5%B8%83/">Distribution (分布)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/seed-%E7%A7%8D%E5%AD%90/">Seed (种子)</a></li> </ul>循环https://terms-en.ai-term-hub.com/zh/terms/loop/Sat, 18 Jul 2026 10:52:50 +0000https://terms-en.ai-term-hub.com/zh/terms/loop/<h2 id="definition">Definition</h2> <p>循环是计算机科学和人工智能开发中的一种基本控制流结构。它允许算法遍历数据集、执行重复计算或运行训练轮次。常见的类型包括for循环和while循环。</p> <h3 id="summary">Summary</h3> <p>一种编程结构，用于在满足条件之前重复执行一段代码块多次。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>迭代</li> <li>控制流</li> <li>轮次 (Epochs)</li> <li>批处理</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>在多轮次中训练神经网络</li> <li>遍历数据集中的样本</li> <li>强化学习的逐步执行</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:#66d9ef">for</span> epoch <span style="color:#f92672">in</span> range(<span style="color:#ae81ff">10</span>): </span></span><span style="display:flex;"><span> <span style="color:#66d9ef">for</span> batch <span style="color:#f92672">in</span> dataloader: </span></span><span style="display:flex;"><span> train_step(batch) </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/iteration-%E8%BF%AD%E4%BB%A3/">Iteration (迭代)</a></li> <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/epoch-%E8%BD%AE%E6%AC%A1/">Epoch (轮次)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/recursion-%E9%80%92%E5%BD%92/">Recursion (递归)</a></li> </ul>信息https://terms-en.ai-term-hub.com/zh/terms/information/Sat, 18 Jul 2026 10:52:05 +0000https://terms-en.ai-term-hub.com/zh/terms/information/<h2 id="definition">Definition</h2> <p>在人工智能和计算机科学的语境中，信息与原始数据有所区别。它代表经过组织、结构化或解释以具有意义和实用性的数据。信息（注：原文截断，此处补全语义）通常被视为数据经过处理后产生的价值体现。</p> <h3 id="summary">Summary</h3> <p>信息是指经过处理的数据，它能够传达意义、减少不确定性或为接收者提供上下文。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>数据与信息</li> <li>熵减</li> <li>语义含义</li> <li>上下文</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>自然语言处理理解</li> <li>决策支持系统</li> <li>知识图谱构建</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/data-%E6%95%B0%E6%8D%AE/">data (数据)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/knowledge-%E7%9F%A5%E8%AF%86/">knowledge (知识)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/intelligence-%E6%99%BA%E8%83%BD/">intelligence (智能)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/semantics-%E8%AF%AD%E4%B9%89%E5%AD%A6/">semantics (语义学)</a></li> </ul>知识https://terms-en.ai-term-hub.com/zh/terms/knowledge/Sat, 18 Jul 2026 10:52:05 +0000https://terms-en.ai-term-hub.com/zh/terms/knowledge/<h2 id="definition">Definition</h2> <p>在人工智能中，知识通常指存储在数据库、本体论或神经网络权重中的显式信息，这些信息允许进行推理和推断。在 DIKW（数据-信息-知识-智慧）层级结构中，知识位于信息之上，代表了更高层次的结构化和可操作的理解。</p> <h3 id="summary">Summary</h3> <p>知识是从信息、经验或推理中得出的结构化理解、事实、技能和见解，能够支持有效的决策制定。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>DIKW 层级</li> <li>推理</li> <li>隐式与显式</li> <li>事实检索</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>问答系统</li> <li>专家系统</li> <li>RAG（检索增强生成）</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/information-%E4%BF%A1%E6%81%AF/">information (信息)</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> <li><a href="https://terms-en.ai-term-hub.com/en/terms/memory-%E8%AE%B0%E5%BF%86/">memory (记忆)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/facts-%E4%BA%8B%E5%AE%9E/">facts (事实)</a></li> </ul>决策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>控制https://terms-en.ai-term-hub.com/zh/terms/control/Sat, 18 Jul 2026 10:49:53 +0000https://terms-en.ai-term-hub.com/zh/terms/control/<h2 id="definition">Definition</h2> <p>在人工智能中，控制是指用于根据当前状态和目标引导系统行为的机制和算法。它涉及反馈回路，其中输出被监控并用于调整后续动作。</p> <h3 id="summary">Summary</h3> <p>通过管理、指导或调节系统的行为和状态以实现预期结果的过程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>反馈回路</li> <li>状态管理</li> <li>执行</li> <li>调节</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>自动驾驶汽车导航</li> <li>机械臂操作</li> <li>工业自动化流程</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/pid-controller-pid%E6%8E%A7%E5%88%B6%E5%99%A8/">PID Controller (PID控制器)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/state-space-%E7%8A%B6%E6%80%81%E7%A9%BA%E9%97%B4/">State Space (状态空间)</a></li> </ul>直接https://terms-en.ai-term-hub.com/zh/terms/direct/Sat, 18 Jul 2026 10:49:53 +0000https://terms-en.ai-term-hub.com/zh/terms/direct/<h2 id="definition">Definition</h2> <p>在AI语境中，“直接”通常描述绕过中间抽象层的架构或推理路径，例如强化学习中的直接策略优化或在端到端系统中直接映射输入到输出。</p> <h3 id="summary">Summary</h3> <p>指将输入直接映射到输出的方法或路径，无需经过中间复杂的变换或潜在表示。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>端到端</li> <li>降低延迟</li> <li>简洁性</li> <li>映射</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>实时控制系统</li> <li>简单回归任务</li> <li>边缘AI部署</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/end-to-end-learning-%E7%AB%AF%E5%88%B0%E7%AB%AF%E5%AD%A6%E4%B9%A0/">End-to-End Learning (端到端学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/regression-%E5%9B%9E%E5%BD%92/">Regression (回归)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/inference-%E6%8E%A8%E7%90%86/">Inference (推理)</a></li> </ul>动作https://terms-en.ai-term-hub.com/zh/terms/action/Sat, 18 Jul 2026 10:49:06 +0000https://terms-en.ai-term-hub.com/zh/terms/action/<h2 id="definition">Definition</h2> <p>在人工智能和机器人技术中，动作是指智能体为与环境交互而采取的具体步骤或决策。动作是基于当前状态选择的。</p> <h3 id="summary">Summary</h3> <p>智能体为影响其环境而执行的操作。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>智能体</li> <li>环境</li> <li>策略</li> <li>状态转移</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>强化学习</li> <li>机器人控制</li> <li>博弈AI</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/observation-%E8%A7%82%E6%B5%8B/">Observation (观测)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/reward-%E5%A5%96%E5%8A%B1/">Reward (奖励)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/policy-%E7%AD%96%E7%95%A5/">Policy (策略)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/state-%E7%8A%B6%E6%80%81/">State (状态)</a></li> </ul>深度学习https://terms-en.ai-term-hub.com/zh/terms/deep_learning/Sat, 18 Jul 2026 07:44:21 +0000https://terms-en.ai-term-hub.com/zh/terms/deep_learning/<h2 id="definition">Definition</h2> <p>深度学习算法试图模拟人脑的分析和学习过程。通过堆叠多个互连节点的层级，这些模型能够从原始数据中学习分层特征，从而在图像识别、语音处理等任务中表现出色。</p> <h3 id="summary">Summary</h3> <p>机器学习的一个子集，使用多层人工神经网络来建模数据中的复杂模式和表示。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>神经网络</li> <li>分层特征</li> <li>非线性建模</li> <li>表示学习</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>语音转文本转换</li> <li>推荐系统</li> <li>自动驾驶感知</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/machine-learning-%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/">Machine Learning (机器学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/artificial-neural-networks-%E4%BA%BA%E5%B7%A5%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C/">Artificial Neural Networks (人工神经网络)</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/big-data-%E5%A4%A7%E6%95%B0%E6%8D%AE/">Big Data (大数据)</a></li> </ul>人工智能https://terms-en.ai-term-hub.com/zh/terms/artificial_intelligence/Sat, 18 Jul 2026 07:44:10 +0000https://terms-en.ai-term-hub.com/zh/terms/artificial_intelligence/<h2 id="definition">Definition</h2> <p>人工智能（AI）是指数字计算机或受计算机控制的机器人执行通常与智能生物相关的任务的能力。它涵盖了各种子领域，包括机器学习、自然语言处理等，旨在让机器具备感知、推理、学习和解决问题的能力。</p> <h3 id="summary">Summary</h3> <p>计算机系统对人类智能过程的模拟。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>机器学习</li> <li>自然语言处理</li> <li>自主性</li> <li>认知计算</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>如 Siri 或 Alexa 的虚拟助手</li> <li>自动驾驶车辆导航</li> <li>医疗诊断支持系统</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/machine-learning-%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/">Machine Learning (机器学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/deep-learning-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/">Deep Learning (深度学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/artificial-general-intelligence-%E9%80%9A%E7%94%A8%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/">Artificial General Intelligence (通用人工智能)</a></li> </ul>