| S-Fold Cross Validation | S 折交叉验证 |
| Saccade | 扫视 |
| Saddle Point | 鞍点 |
| Saddle-Free Newton Method | 无鞍牛顿法 |
| Saliency Map | 显著图 |
| Saliency-Based Attention | 基于显著性的注意力 |
| Same | 相同 |
| Sample | 样本 |
| Sample Complexity | 样本复杂度 |
| Sample Mean | 样本均值 |
| Sample Space | 样本空间 |
| Sample Variance | 样本方差 |
| Sampling | 采样 |
| Sampling Method | 采样法 |
| Saturate | 饱和 |
| Saturating Function | 饱和函数 |
| Scalar | 标量 |
| Scale Invariance | 尺度不变性 |
| Scatter Matrix | 散布矩阵 |
| Scheduled Sampling | 计划采样 |
| Score | 得分 |
| Score Function | 评分函数 |
| Score Matching | 分数匹配 |
| Second Derivative | 二阶导数 |
| Second Derivative Test | 二阶导数测试 |
| Second Layer | 第二层 |
| Second-Order Method | 二阶方法 |
| Selective Attention | 选择性注意力 |
| Selective Ensemble | 选择性集成 |
| Self Information | 自信息 |
| Self-Attention | 自注意力 |
| Self-Attention Model | 自注意力模型 |
| Self-Contrastive Estimation | 自对比估计 |
| Self-Driving | 自动驾驶 |
| Self-Gated | 自门控 |
| Self-Organizing Map | 自组织映射网 | SOM |
| Self-Taught Learning | 自学习 |
| Self-Training | 自训练 |
| Semantic Gap | 语义鸿沟 |
| Semantic Hashing | 语义哈希 |
| Semantic Segmentation | 语义分割 |
| Semantic Similarity | 语义相似度 |
| Semi-Definite Programming | 半正定规划 |
| Semi-Naive Bayes Classifiers | 半朴素贝叶斯分类器 |
| Semi-Restricted Boltzmann Machine | 半受限玻尔兹曼机 |
| Semi-Supervised | 半监督 |
| Semi-Supervised Clustering | 半监督聚类 |
| Semi-Supervised Learning | 半监督学习 |
| Semi-Supervised Support Vector Machine | 半监督支持向量机 | S3VM |
| Sentiment Analysis | 情感分析 |
| Separable | 可分离的 |
| Separate | 分离的 |
| Separating Hyperplane | 分离超平面 |
| Separation | 分离 |
| Sequence Labeling | 序列标注 |
| Sequence To Sequence Learning | 序列到序列学习 | Seq2Seq |
| Sequence-To-Sequence | 序列到序列 | Seq2Seq |
| Sequential Covering | 序贯覆盖 |
| Sequential Minimal Optimization | 序列最小最优化 | SMO |
| Sequential Model-Based Optimization | 时序模型优化 | SMBO |
| Sequential Partitioning | 顺序分区 |
| Setting | 情景 |
| Shadow Circuit | 浅度回路 |
| Shallow Learning | 浅层学习 |
| Shannon Entropy | 香农熵 |
| Shannons | 香农 |
| Shaping | 塑造 |
| Sharp Minima | 尖锐最小值 |
| Shattering | 打散 |
| Shift Invariance | 平移不变性 |
| Short-Term Memory | 短期记忆 |
| Shortcut Connection | 直连边 |
| Shortlist | 短列表 |
| Siamese Network | 孪生网络 |
| Sigmoid | Sigmoid（一种激活函数） | 统计 |
| Sigmoid Belief Network | Sigmoid信念网络 | SBN |
| Sigmoid Curve | S 形曲线 |
| Sigmoid Function | Sigmoid函数 |
| Sign Function | 符号函数 |
| Signed Distance | 带符号距离 |
| Similarity | 相似度 |
| Similarity Measure | 相似度度量 |
| Simple Cell | 简单细胞 |
| Simple Recurrent Network | 简单循环网络 | SRN |
| Simple Recurrent Neural Network | 简单循环神经网络 | S-RNN |
| Simplex | 单纯形 |
| Simulated Annealing | 模拟退火 | 统计、机器学习 |
| Simultaneous Localization And Mapping | 即时定位与地图构建 | SLAM |
| Single Component Metropolis-Hastings | 单分量Metropolis-Hastings |
| Single Linkage | 单连接 |
| Singular | 奇异的 |
| Singular Value | 奇异值 |
| Singular Value Decomposition | 奇异值分解 | SVD |
| Singular Vector | 奇异向量 |
| Size | 大小 |
| Skip Connection | 跳跃连接 |
| Skip-Gram Model | 跳元模型 |
| Skip-Gram Model With Negative Sampling | 跳元模型加负采样 |
| Slack Variable | 松弛变量 |
| Slow Feature Analysis | 慢特征分析 |
| Slowness Principle | 慢性原则 |
| Smoothing | 平滑 |
| Smoothness Prior | 平滑先验 |
| Soft Attention Mechanism | 软性注意力机制 |
| Soft Clustering | 软聚类 |
| Soft Margin | 软间隔 |
| Soft Margin Maximization | 软间隔最大化 |
| Soft Target | 软目标 |
| Soft Voting | 软投票 |
| Softmax | Softmax/软最大化 |
| Softmax Function | Softmax函数/软最大化函数 | 统计、机器学习 |
| Softmax Regression | Softmax回归/软最大化回归 |
| Softmax Unit | Softmax单元/软最大化单元 |
| Softplus | Softplus |
| Softplus Function | Softplus函数 |
| Source Domain | 源领域 |
| Span | 张成子空间 |
| Sparse | 稀疏 |
| Sparse Activation | 稀疏激活 |
| Sparse Auto-Encoder | 稀疏自编码器 |
| Sparse Coding | 稀疏编码 |
| Sparse Connectivity | 稀疏连接 |
| Sparse Initialization | 稀疏初始化 |
| Sparse Interactions | 稀疏交互 |
| Sparse Representation | 稀疏表示 |
| Sparse Weights | 稀疏权重 |
| Sparsity | 稀疏性 |
| Specialization | 特化 |
| Spectral Clustering | 谱聚类 |
| Spectral Radius | 谱半径 |
| Speech Recognition | 语音识别 |
| Sphering | Sphering |
| Spike And Slab | 尖峰和平板 |
| Spike And Slab RBM | 尖峰和平板RBM |
| Spiking Neural Nets | 脉冲神经网络 |
| Splitting Point | 切分点 |
| Splitting Variable | 切分变量 |
| Spurious Modes | 虚假模态 |
| Square | 方阵 |
| Square Loss | 平方损失 |
| Squared Euclidean Distance | 欧氏距离平方 |
| Squared Exponential | 平方指数 |
| Squashing Function | 挤压函数 |
| Stability | 稳定性 |
| Stability-Plasticity Dilemma | 可塑性-稳定性窘境 |
| Stable Base Learner | 稳定基学习器 |
| Stacked Auto-Encoder | 堆叠自编码器 | SAE |
| Stacked Deconvolutional Network | 堆叠解卷积网络 | SDN |
| Stacked Recurrent Neural Network | 堆叠循环神经网络 | SRNN |
| Standard Basis | 标准基 |
| Standard Deviation | 标准差 |
| Standard Error | 标准差 |
| Standard Normal Distribution | 标准正态分布 |
| Standardization | 标准化 |
| State | 状态 |
| State Action Reward State Action | SARSA算法 | SARSA |
| State Sequence | 状态序列 |
| State Space | 状态空间 |
| State Value Function | 状态值函数 |
| State-Action Value Function | 状态-动作值函数 |
| Statement | 声明 |
| Static Computational Graph | 静态计算图 |
| Static Game | 静态博弈 |
| Stationary | 平稳的 |
| Stationary Distribution | 平稳分布 |
| Stationary Point | 驻点 |
| Statistic Efficiency | 统计效率 |
| Statistical Learning | 统计学习 |
| Statistical Learning Theory | 统计学习理论 |
| Statistical Machine Learning | 统计机器学习 |
| Statistical Relational Learning | 统计关系学习 |
| Statistical Simulation Method | 统计模拟方法 |
| Statistics | 统计量 |
| Status Feature Function | 状态特征函数 |
| Steepest Descent | 最速下降法 |
| Step Decay | 阶梯衰减 |
| Stochastic | 随机 |
| Stochastic Curriculum | 随机课程 |
| Stochastic Dynamical System | 随机动力系统 |
| Stochastic Gradient Ascent | 随机梯度上升 |
| Stochastic Gradient Descent | 随机梯度下降 |
| Stochastic Gradient Descent With Warm Restarts | 带热重启的随机梯度下降 | SGDR |
| Stochastic Matrix | 随机矩阵 |
| Stochastic Maximum Likelihood | 随机最大似然 |
| Stochastic Neighbor Embedding | 随机近邻嵌入 |
| Stochastic Neural Network | 随机神经网络 | SNN |
| Stochastic Policy | 随机性策略 |
| Stochastic Process | 随机过程 |
| Stop Words | 停用词 |
| Stratified Sampling | 分层采样 |
| Stream | 流 |
| Stride | 步幅 |
| String Kernel Function | 字符串核函数 |
| Strong Classifier | 强分类器 |
| Strong Duality | 强对偶性 |
| Strongly Connected Graph | 强连通图 |
| Strongly Learnable | 强可学习 |
| Structural Risk | 结构风险 |
| Structural Risk Minimization | 结构风险最小化 | SRM |
| Structure Learning | 结构学习 |
| Structured Learning | 结构化学习 |
| Structured Probabilistic Model | 结构化概率模型 |
| Structured Variational Inference | 结构化变分推断 |
| Student Network | 学生网络 |
| Sub-Optimal | 次最优 |
| Subatomic | 亚原子 |
| Subsample | 子采样 |
| Subsampling | 下采样 |
| Subsampling Layer | 子采样层 |
| Subset Evaluation | 子集评价 |
| Subset Search | 子集搜索 |
| Subspace | 子空间 |
| Substitution | 置换 |
| Successive Halving | 逐次减半 |
| Sum Rule | 求和法则 |
| Sum-Product | 和积 |
| Sum-Product Network | 和-积网络 |
| Super-Parent | 超父 |
| Supervised | 监督 |
| Supervised Learning | 监督学习 | 机器学习 |
| Supervised Learning Algorithm | 监督学习算法 |
| Supervised Model | 监督模型 |
| Supervised Pretraining | 监督预训练 |
| Support Vector | 支持向量 | 统计、机器学习 |
| Support Vector Expansion | 支持向量展式 |
| Support Vector Machine | 支持向量机 | SVM | 统计、机器学习 |
| Support Vector Regression | 支持向量回归 | SVR | 统计、机器学习 |
| Surrogat Loss | 替代损失 |
| Surrogate Function | 替代函数 |
| Surrogate Loss Function | 代理损失函数 |
| Symbol | 符号 |
| Symbolic Differentiation | 符号微分 |
| Symbolic Learning | 符号学习 |
| Symbolic Representation | 符号表示 |
| Symbolism | 符号主义 |
| Symmetric | 对称 |
| Symmetric Matrix | 对称矩阵 |
| Synonymy | 多词一义性 |
| Synset | 同义词集 |
| Synthetic Feature | 合成特征 |
| Scaling | 缩放 | 图像处理 |
| Simulation | 仿真 |
| Sequence-Function | 序列-功能 |
| Set Prediction | 集合预测 |
| stuff categories | 填充类别 | 全景分割中，天空、墙面、地面等不规则的类别 |
