| 1 | Accept-Reject Sampling Method | 接受-拒绝抽样法/接受-拒绝采样法 |
| 2 | Accumulated Error Backpropagation | 累积误差反向传播 |
| 3 | Accuracy | 准确率 |
| 4 | Acquisition Function | 采集函数 |
| 5 | Action | 动作 |
| 6 | Activation Function | 激活函数 |
| 7 | Active Learning | 主动学习 |
| 8 | Adaptive Bitrate Algorithm | 自适应比特率算法 |
| 9 | Adaptive Boosting | AdaBoost |
| 10 | Adaptive Gradient Algorithm | AdaGrad |
| 11 | Adaptive Moment Estimation Algorithm | Adam算法 |
| 12 | Adaptive Resonance Theory | 自适应谐振理论 |
| 13 | Additive Model | 加性模型 |
| 14 | Affinity Matrix | 亲和矩阵 |
| 15 | Agent | 智能体 |
| 16 | Algorithm | 算法 |
| 17 | Alpha-Beta Pruning | α-β修剪法 |
| 18 | Anomaly Detection | 异常检测 |
| 19 | Approximate Inference | 近似推断 |
| 20 | Area Under ROC Curve | AUC(ROC曲线下方面积,度量分类模型好坏的标准) |
| 21 | Artificial Intelligence | 人工智能 |
| 22 | Artificial Neural Network | 人工神经网络 |
| 23 | Artificial Neuron | 人工神经元 |
| 24 | Attention | 注意力 |
| 25 | Attention Mechanism | 注意力机制 |
| 26 | Attribute | 属性 |
| 27 | Attribute Space | 属性空间 |
| 28 | Autoencoder | 自编码器 |
| 29 | Automatic Differentiation | 自动微分 |
| 30 | Autoregressive Model | 自回归模型 |
| 31 | BFGS | BFGS |
| 32 | Back Propagation | 反向传播 |
| 33 | Back Propagation Algorithm | 反向传播算法 |
| 34 | Back Propagation Through Time | 随时间反向传播 |
| 35 | Backward Induction | 反向归纳 |
| 36 | Backward Search | 反向搜索 |
| 37 | Bag of Words | 词袋 |
| 38 | Bandit | 赌博机/老虎机 |
| 39 | Base Learner | 基学习器 |
| 40 | Base Learning Algorithm | 基学习算法 |
| 41 | Baseline | 基准 |
| 42 | Batch | 批量 |
| 43 | Batch Normalization | 批量规范化 |
| 44 | Bayes Decision Rule | 贝叶斯决策准则 |
| 45 | Bayes Model Averaging | 贝叶斯模型平均 |
| 46 | Bayes Optimal Classifier | 贝叶斯最优分类器 |
| 47 | Bayes' Theorem | 贝叶斯定理 |
| 48 | Bayesian Decision Theory | 贝叶斯决策理论 |
| 49 | Bayesian Inference | 贝叶斯推断 |
| 50 | Bayesian Learning | 贝叶斯学习 |
| 51 | Bayesian Network | 贝叶斯网/贝叶斯网络 |
| 52 | Bayesian Optimization | 贝叶斯优化 |
| 53 | Beam Search | 束搜索 |
| 54 | Belief Network | 信念网/信念网络 |
| 55 | Belief Propagation | 信念传播 |
| 56 | Bellman Equation | 贝尔曼方程 |
| 57 | Benchmark | 基准 |
| 58 | Bernoulli Distribution | 伯努利分布 |
| 59 | Beta Distribution | 贝塔分布 |
| 60 | Between-Class Scatter Matrix | 类间散度矩阵 |
| 61 | Bias | 偏差/偏置 |
| 62 | Bias In Affine Function | 偏置 |
| 63 | Bias In Statistics | 偏差 |
| 64 | Bias Shift | 偏置偏移 |
| 65 | Bias-Variance Decomposition | 偏差 - 方差分解 |
| 66 | Bias-Variance Dilemma | 偏差 - 方差困境 |
| 67 | Bidirectional Recurrent Neural Network | 双向循环神经网络 |
| 68 | Bigram | 二元语法 |
| 69 | Bilingual Evaluation Understudy | BLEU |
| 70 | Binary Classification | 二分类 |
| 71 | Binomial Distribution | 二项分布 |
| 72 | Binomial Test | 二项检验 |
| 73 | Boltzmann Distribution | 玻尔兹曼分布 |
| 74 | Boltzmann Machine | 玻尔兹曼机 |
| 75 | Boosting | Boosting(一种模型训练加速方式) |
| 76 | Bootstrap Aggregating | Bagging |
| 77 | Bootstrap Sampling | 自助采样法 |
| 78 | Bootstrapping | 自助法/自举法 |
| 79 | Break-Event Point | 平衡点 |
| 80 | Bucketing | 分桶 |
| 81 | Calculus of Variations | 变分法 |
| 82 | Cascade-Correlation | 级联相关 |
| 83 | Catastrophic Forgetting | 灾难性遗忘 |
| 84 | Categorical Distribution | 类别分布 |
| 85 | Cell | 单元 |
| 86 | Chain Rule | 链式法则 |
| 87 | Chebyshev Distance | 切比雪夫距离 |
| 88 | Class | 类别 |
| 89 | Class-Imbalance | 类别不平衡 |
| 90 | Classification | 分类 |
| 91 | Classification And Regression Tree | 分类与回归树 |
| 92 | Classifier | 分类器 |
| 93 | Clique | 团 |
| 94 | Cluster | 簇 |
| 95 | Cluster Assumption | 聚类假设 |
| 96 | Clustering | 聚类 |
| 97 | Clustering Ensemble | 聚类集成 |
| 98 | Co-Training | 协同训练 |
| 99 | Coding Matrix | 编码矩阵 |
| 100 | Collaborative Filtering | 协同过滤 |
| 101 | Competitive Learning | 竞争型学习 |
| 102 | Comprehensibility | 可解释性 |
| 103 | Computation Graph | 计算图 |
| 104 | Computational Learning Theory | 计算学习理论 |
| 105 | Conditional Entropy | 条件熵 |
| 106 | Conditional Probability | 条件概率 |
| 107 | Conditional Probability Distribution | 条件概率分布 |
| 108 | Conditional Random Field | 条件随机场 |
| 109 | Conditional Risk | 条件风险 |
| 110 | Confidence | 置信度 |
| 111 | Confusion Matrix | 混淆矩阵 |
| 112 | Conjugate Distribution | 共轭分布 |
| 113 | Connection Weight | 连接权 |
| 114 | Connectionism | 连接主义 |
| 115 | Consistency | 一致性 |
| 116 | Constrained Optimization | 约束优化 |
| 117 | Context Variable | 上下文变量 |
| 118 | Context Vector | 上下文向量 |
| 119 | Context Window | 上下文窗口 |
| 120 | Context Word | 上下文词 |
| 121 | Contextual Bandit | 上下文赌博机/上下文老虎机 |
| 122 | Contingency Table | 列联表 |
| 123 | Continuous Attribute | 连续属性 |
| 124 | Contrastive Divergence | 对比散度 |
| 125 | Convergence | 收敛 |
| 126 | Convex Optimization | 凸优化 |
| 127 | Convex Quadratic Programming | 凸二次规划 |
| 128 | Convolution | 卷积 |
| 129 | Convolutional Kernel | 卷积核 |
| 130 | Convolutional Neural Network | 卷积神经网络 |
| 131 | Coordinate Descent | 坐标下降 |
| 132 | Corpus | 语料库 |
| 133 | Correlation Coefficient | 相关系数 |
| 134 | Cosine Similarity | 余弦相似度 |
| 135 | Cost | 代价 |
| 136 | Cost Curve | 代价曲线 |
| 137 | Cost Function | 代价函数 |
| 138 | Cost Matrix | 代价矩阵 |
| 139 | Cost-Sensitive | 代价敏感 |
| 140 | Covariance | 协方差 |
| 141 | Covariance Matrix | 协方差矩阵 |
| 142 | Critical Point | 临界点 |
| 143 | Cross Entropy | 交叉熵 |
| 144 | Cross Validation | 交叉验证 |
| 145 | Curse of Dimensionality | 维数灾难 |
| 146 | Cutting Plane Algorithm | 割平面法 |
| 147 | Data Mining | 数据挖掘 |
| 148 | Data Set | 数据集 |
| 149 | Davidon-Fletcher-Powell | DFP |
| 150 | Decision Boundary | 决策边界 |
| 151 | Decision Function | 决策函数 |
| 152 | Decision Stump | 决策树桩 |
| 153 | Decision Tree | 决策树 |
| 154 | Decoder | 解码器 |
| 155 | Decoding | 解码 |
| 156 | Deconvolution | 反卷积 |
| 157 | Deconvolutional Network | 反卷积网络 |
| 158 | Deduction | 演绎 |
| 159 | Deep Belief Network | 深度信念网络 |
| 160 | Deep Boltzmann Machine | 深度玻尔兹曼机 |
| 161 | Deep Convolutional Generative Adversarial Network | 深度卷积生成对抗网络 |
| 162 | Deep Learning | 深度学习 |
| 163 | Deep Neural Network | 深度神经网络 |
| 164 | Deep Q-Network | 深度Q网络 |
| 165 | Delta-Bar-Delta | Delta-Bar-Delta |
| 166 | Denoising | 去噪 |
| 167 | Denoising Autoencoder | 去噪自编码器 |
| 168 | Denoising Score Matching | 去躁分数匹配 |
| 169 | Density Estimation | 密度估计 |
| 170 | Density-Based Clustering | 密度聚类 |
| 171 | Derivative | 导数 |
| 172 | Determinant | 行列式 |
| 173 | Diagonal Matrix | 对角矩阵 |
| 174 | Dictionary Learning | 字典学习 |
| 175 | Dimension Reduction | 降维 |
| 176 | Directed Edge | 有向边 |
| 177 | Directed Graphical Model | 有向图模型 |
| 178 | Directed Separation | 有向分离 |
| 179 | Dirichlet Distribution | 狄利克雷分布 |
| 180 | Discriminative Model | 判别式模型 |
| 181 | Discriminator | 判别器 |
| 182 | Discriminator Network | 判别网络 |
| 183 | Distance Measure | 距离度量 |
| 184 | Distance Metric Learning | 距离度量学习 |
| 185 | Distributed Representation | 分布式表示 |
| 186 | Diverge | 发散 |
| 187 | Divergence | 散度 |
| 188 | Diversity | 多样性 |
| 189 | Diversity Measure | 多样性度量/差异性度量 |
| 190 | Domain Adaptation | 领域自适应 |
| 191 | Dominant Eigenvalue | 主特征值 |
| 192 | Dominant Strategy | 占优策略 |
| 193 | Down Sampling | 下采样 |
| 194 | Dropout | 暂退法 |
| 195 | Dropout Boosting | 暂退Boosting |
| 196 | Dropout Method | 暂退法 |
| 197 | Dual Problem | 对偶问题 |
| 198 | Dummy Node | 哑结点 |
| 199 | Dynamic Bayesian Network | 动态贝叶斯网络 |
| 200 | Dynamic Programming | 动态规划 |