qwerty-learner/public/dicts/ai_machine_learning.json

[
  {
      "name": "Loss Function",
      "trans": [
          "损失函数"
      ]
  },
  {
      "name": "Accept-Reject Sampling Method",
      "trans": [
          "接受-拒绝抽样法/接受-拒绝采样法"
      ]
  },
  {
      "name": "Accumulated Error Backpropagation",
      "trans": [
          "累积误差反向传播"
      ]
  },
  {
      "name": "Accuracy",
      "trans": [
          "准确率"
      ]
  },
  {
      "name": "Acquisition Function",
      "trans": [
          "采集函数"
      ]
  },
  {
      "name": "Action",
      "trans": [
          "动作"
      ]
  },
  {
      "name": "Activation Function",
      "trans": [
          "激活函数"
      ]
  },
  {
      "name": "Active Learning",
      "trans": [
          "主动学习"
      ]
  },
  {
      "name": "Adaptive Bitrate Algorithm",
      "trans": [
          "自适应比特率算法"
      ]
  },
  {
      "name": "Adaptive Boosting",
      "trans": [
          "AdaBoost"
      ]
  },
  {
      "name": "Adaptive Gradient Algorithm",
      "trans": [
          "AdaGrad"
      ]
  },
  {
      "name": "Adaptive Moment Estimation Algorithm",
      "trans": [
          "Adam算法"
      ]
  },
  {
      "name": "Adaptive Resonance Theory",
      "trans": [
          "自适应谐振理论"
      ]
  },
  {
      "name": "Additive Model",
      "trans": [
          "加性模型"
      ]
  },
  {
      "name": "Affinity Matrix",
      "trans": [
          "亲和矩阵"
      ]
  },
  {
      "name": "Agent",
      "trans": [
          "智能体"
      ]
  },
  {
      "name": "Algorithm",
      "trans": [
          "算法"
      ]
  },
  {
      "name": "Alpha-Beta Pruning",
      "trans": [
          "α-β修剪法"
      ]
  },
  {
      "name": "Anomaly Detection",
      "trans": [
          "异常检测"
      ]
  },
  {
      "name": "Approximate Inference",
      "trans": [
          "近似推断"
      ]
  },
  {
      "name": "Area Under ROC Curve",
      "trans": [
          "AUC（ROC曲线下方面积，度量分类模型好坏的标准）"
      ]
  },
  {
      "name": "Artificial Intelligence",
      "trans": [
          "人工智能"
      ]
  },
  {
      "name": "Artificial Neural Network",
      "trans": [
          "人工神经网络"
      ]
  },
  {
      "name": "Artificial Neuron",
      "trans": [
          "人工神经元"
      ]
  },
  {
      "name": "Attention",
      "trans": [
          "注意力"
      ]
  },
  {
      "name": "Attention Mechanism",
      "trans": [
          "注意力机制"
      ]
  },
  {
      "name": "Attribute",
      "trans": [
          "属性"
      ]
  },
  {
      "name": "Attribute Space",
      "trans": [
          "属性空间"
      ]
  },
  {
      "name": "Autoencoder",
      "trans": [
          "自编码器"
      ]
  },
  {
      "name": "Automatic Differentiation",
      "trans": [
          "自动微分"
      ]
  },
  {
      "name": "Autoregressive Model",
      "trans": [
          "自回归模型"
      ]
  },
  {
      "name": "Back Propagation",
      "trans": [
          "反向传播"
      ]
  },
  {
      "name": "Back Propagation Algorithm",
      "trans": [
          "反向传播算法"
      ]
  },
  {
      "name": "Back Propagation Through Time",
      "trans": [
          "随时间反向传播"
      ]
  },
  {
      "name": "Backward Induction",
      "trans": [
          "反向归纳"
      ]
  },
  {
      "name": "Backward Search",
      "trans": [
          "反向搜索"
      ]
  },
  {
      "name": "Bag of Words",
      "trans": [
          "词袋"
      ]
  },
  {
      "name": "Bandit",
      "trans": [
          "赌博机/老虎机"
      ]
  },
  {
      "name": "Base Learner",
      "trans": [
          "基学习器"
      ]
  },
  {
      "name": "Base Learning Algorithm",
      "trans": [
          "基学习算法"
      ]
  },
  {
      "name": "Baseline",
      "trans": [
          "基准"
      ]
  },
  {
      "name": "Batch",
      "trans": [
          "批量"
      ]
  },
  {
      "name": "Batch Normalization",
      "trans": [
          "批量规范化"
      ]
  },
  {
      "name": "Bayes Decision Rule",
      "trans": [
          "贝叶斯决策准则"
      ]
  },
  {
      "name": "Bayes Model Averaging",
      "trans": [
          "贝叶斯模型平均"
      ]
  },
  {
      "name": "Bayes Optimal Classifier",
      "trans": [
          "贝叶斯最优分类器"
      ]
  },
  {
      "name": "Bayes' Theorem",
      "trans": [
          "贝叶斯定理"
      ]
  },
  {
      "name": "Bayesian Decision Theory",
      "trans": [
          "贝叶斯决策理论"
      ]
  },
  {
      "name": "Bayesian Inference",
      "trans": [
          "贝叶斯推断"
      ]
  },
  {
      "name": "Bayesian Learning",
      "trans": [
          "贝叶斯学习"
      ]
  },
  {
      "name": "Bayesian Network",
      "trans": [
          "贝叶斯网/贝叶斯网络"
      ]
  },
  {
      "name": "Bayesian Optimization",
      "trans": [
          "贝叶斯优化"
      ]
  },
  {
      "name": "Beam Search",
      "trans": [
          "束搜索"
      ]
  },
  {
      "name": "Benchmark",
      "trans": [
          "基准"
      ]
  },
  {
      "name": "Belief Network",
      "trans": [
          "信念网/信念网络"
      ]
  },
  {
      "name": "Belief Propagation",
      "trans": [
          "信念传播"
      ]
  },
  {
      "name": "Bellman Equation",
      "trans": [
          "贝尔曼方程"
      ]
  },
  {
      "name": "Bernoulli Distribution",
      "trans": [
          "伯努利分布"
      ]
  },
  {
      "name": "Beta Distribution",
      "trans": [
          "贝塔分布"
      ]
  },
  {
      "name": "Between-Class Scatter Matrix",
      "trans": [
          "类间散度矩阵"
      ]
  },
  {
      "name": "BFGS",
      "trans": [
          "BFGS"
      ]
  },
  {
      "name": "Bias",
      "trans": [
          "偏差/偏置"
      ]
  },
  {
      "name": "Bias In Affine Function",
      "trans": [
          "偏置"
      ]
  },
  {
      "name": "Bias In Statistics",
      "trans": [
          "偏差"
      ]
  },
  {
      "name": "Bias Shift",
      "trans": [
          "偏置偏移"
      ]
  },
  {
      "name": "Bias-Variance Decomposition",
      "trans": [
          "偏差 - 方差分解"
      ]
  },
  {
      "name": "Bias-Variance Dilemma",
      "trans": [
          "偏差 - 方差困境"
      ]
  },
  {
      "name": "Bidirectional Recurrent Neural Network",
      "trans": [
          "双向循环神经网络"
      ]
  },
  {
      "name": "Bigram",
      "trans": [
          "二元语法"
      ]
  },
  {
      "name": "Bilingual Evaluation Understudy",
      "trans": [
          "BLEU"
      ]
  },
  {
      "name": "Binary Classification",
      "trans": [
          "二分类"
      ]
  },
  {
      "name": "Binomial Distribution",
      "trans": [
          "二项分布"
      ]
  },
  {
      "name": "Binomial Test",
      "trans": [
          "二项检验"
      ]
  },
  {
      "name": "Boltzmann Distribution",
      "trans": [
          "玻尔兹曼分布"
      ]
  },
  {
      "name": "Boltzmann Machine",
      "trans": [
          "玻尔兹曼机"
      ]
  },
  {
      "name": "Boosting",
      "trans": [
          "Boosting（一种模型训练加速方式）"
      ]
  },
  {
      "name": "Bootstrap Aggregating",
      "trans": [
          "Bagging"
      ]
  },
  {
      "name": "Bootstrap Sampling",
      "trans": [
          "自助采样法"
      ]
  },
  {
      "name": "Bootstrapping",
      "trans": [
          "自助法/自举法"
      ]
  },
  {
      "name": "Break-Event Point",
      "trans": [
          "平衡点"
      ]
  },
  {
      "name": "Bucketing",
      "trans": [
          "分桶"
      ]
  },
  {
      "name": "Calculus of Variations",
      "trans": [
          "变分法"
      ]
  },
  {
      "name": "Cascade-Correlation",
      "trans": [
          "级联相关"
      ]
  },
  {
      "name": "Catastrophic Forgetting",
      "trans": [
          "灾难性遗忘"
      ]
  },
  {
      "name": "Categorical Distribution",
      "trans": [
          "类别分布"
      ]
  },
  {
      "name": "Cell",
      "trans": [
          "单元"
      ]
  },
  {
      "name": "Chain Rule",
      "trans": [
          "链式法则"
      ]
  },
  {
      "name": "Chebyshev Distance",
      "trans": [
          "切比雪夫距离"
      ]
  },
  {
      "name": "Class",
      "trans": [
          "类别"
      ]
  },
  {
      "name": "Class-Imbalance",
      "trans": [
          "类别不平衡"
      ]
  },
  {
      "name": "Classification",
      "trans": [
          "分类"
      ]
  },
  {
      "name": "Classification And Regression Tree",
      "trans": [
          "分类与回归树"
      ]
  },
  {
      "name": "Classifier",
      "trans": [
          "分类器"
      ]
  },
  {
      "name": "Clique",
      "trans": [
          "团"
      ]
  },
  {
      "name": "Cluster",
      "trans": [
          "簇"
      ]
  },
  {
      "name": "Cluster Assumption",
      "trans": [
          "聚类假设"
      ]
  },
  {
      "name": "Clustering",
      "trans": [
          "聚类"
      ]
  },
  {
      "name": "Clustering Ensemble",
      "trans": [
          "聚类集成"
      ]
  },
  {
      "name": "Co-Training",
      "trans": [
          "协同训练"
      ]
  },
  {
      "name": "Coding Matrix",
      "trans": [
          "编码矩阵"
      ]
  },
  {
      "name": "Collaborative Filtering",
      "trans": [
          "协同过滤"
      ]
  },
  {
      "name": "Competitive Learning",
      "trans": [
          "竞争型学习"
      ]
  },
  {
      "name": "Comprehensibility",
      "trans": [
          "可解释性"
      ]
  },
  {
      "name": "Computation Graph",
      "trans": [
          "计算图"
      ]
  },
  {
      "name": "Computational Learning Theory",
      "trans": [
          "计算学习理论"
      ]
  },
  {
      "name": "Conditional Entropy",
      "trans": [
          "条件熵"
      ]
  },
  {
      "name": "Conditional Probability",
      "trans": [
          "条件概率"
      ]
  },
  {
      "name": "Conditional Probability Distribution",
      "trans": [
          "条件概率分布"
      ]
  },
  {
      "name": "Conditional Random Field",
      "trans": [
          "条件随机场"
      ]
  },
  {
      "name": "Conditional Risk",
      "trans": [
          "条件风险"
      ]
  },
  {
      "name": "Confidence",
      "trans": [
          "置信度"
      ]
  },
  {
      "name": "Confusion Matrix",
      "trans": [
          "混淆矩阵"
      ]
  },
  {
      "name": "Conjugate Distribution",
      "trans": [
          "共轭分布"
      ]
  },
  {
      "name": "Connection Weight",
      "trans": [
          "连接权"
      ]
  },
  {
      "name": "Connectionism",
      "trans": [
          "连接主义"
      ]
  },
  {
      "name": "Consistency",
      "trans": [
          "一致性"
      ]
  },
  {
      "name": "Constrained Optimization",
      "trans": [
          "约束优化"
      ]
  },
  {
      "name": "Context Variable",
      "trans": [
          "上下文变量"
      ]
  },
  {
      "name": "Context Vector",
      "trans": [
          "上下文向量"
      ]
  },
  {
      "name": "Context Window",
      "trans": [
          "上下文窗口"
      ]
  },
  {
      "name": "Context Word",
      "trans": [
          "上下文词"
      ]
  },
  {
      "name": "Contextual Bandit",
      "trans": [
          "上下文赌博机/上下文老虎机"
      ]
  },
  {
      "name": "Contingency Table",
      "trans": [
          "列联表"
      ]
  },
  {
      "name": "Continuous Attribute",
      "trans": [
          "连续属性"
      ]
  },
  {
      "name": "Contrastive Divergence",
      "trans": [
          "对比散度"
      ]
  },
  {
      "name": "Convergence",
      "trans": [
          "收敛"
      ]
  },
  {
      "name": "Convex Optimization",
      "trans": [
          "凸优化"
      ]
  },
  {
      "name": "Convex Quadratic Programming",
      "trans": [
          "凸二次规划"
      ]
  },
  {
      "name": "Convolution",
      "trans": [
          "卷积"
      ]
  },
  {
      "name": "Convolutional Kernel",
      "trans": [
          "卷积核"
      ]
  },
  {
      "name": "Convolutional Neural Network",
      "trans": [
          "卷积神经网络"
      ]
  },
  {
      "name": "Coordinate Descent",
      "trans": [
          "坐标下降"
      ]
  },
  {
      "name": "Corpus",
      "trans": [
          "语料库"
      ]
  },
  {
      "name": "Correlation Coefficient",
      "trans": [
          "相关系数"
      ]
  },
  {
      "name": "Cosine Similarity",
      "trans": [
          "余弦相似度"
      ]
  },
  {
      "name": "Cost",
      "trans": [
          "代价"
      ]
  },
  {
      "name": "Cost Curve",
      "trans": [
          "代价曲线"
      ]
  },
  {
      "name": "Cost Function",
      "trans": [
          "代价函数"
      ]
  },
  {
      "name": "Cost Matrix",
      "trans": [
          "代价矩阵"
      ]
  },
  {
      "name": "Cost-Sensitive",
      "trans": [
          "代价敏感"
      ]
  },
  {
      "name": "Covariance",
      "trans": [
          "协方差"
      ]
  },
  {
      "name": "Covariance Matrix",
      "trans": [
          "协方差矩阵"
      ]
  },
  {
      "name": "Critical Point",
      "trans": [
          "临界点"
      ]
  },
  {
      "name": "Cross Entropy",
      "trans": [
          "交叉熵"
      ]
  },
  {
      "name": "Cross Validation",
      "trans": [
          "交叉验证"
      ]
  },
  {
      "name": "Curse of Dimensionality",
      "trans": [
          "维数灾难"
      ]
  },
  {
      "name": "Cutting Plane Algorithm",
      "trans": [
          "割平面法"
      ]
  },
  {
      "name": "Data Mining",
      "trans": [
          "数据挖掘"
      ]
  },
  {
      "name": "Data Set",
      "trans": [
          "数据集"
      ]
  },
  {
      "name": "Davidon-Fletcher-Powell",
      "trans": [
          "DFP"
      ]
  },
  {
      "name": "Decision Boundary",
      "trans": [
          "决策边界"
      ]
  },
  {
      "name": "Decision Function",
      "trans": [
          "决策函数"
      ]
  },
  {
      "name": "Decision Stump",
      "trans": [
          "决策树桩"
      ]
  },
  {
      "name": "Decision Tree",
      "trans": [
          "决策树"
      ]
  },
  {
      "name": "Decoder",
      "trans": [
          "解码器"
      ]
  },
  {
      "name": "Decoding",
      "trans": [
          "解码"
      ]
  },
  {
      "name": "Deconvolution",
      "trans": [
          "反卷积"
      ]
  },
  {
      "name": "Deconvolutional Network",
      "trans": [
          "反卷积网络"
      ]
  },
  {
      "name": "Deduction",
      "trans": [
          "演绎"
      ]
  },
  {
      "name": "Deep Belief Network",
      "trans": [
          "深度信念网络"
      ]
  },
  {
      "name": "Deep Boltzmann Machine",
      "trans": [
          "深度玻尔兹曼机"
      ]
  },
  {
      "name": "Deep Convolutional Generative Adversarial Network",
      "trans": [
          "深度卷积生成对抗网络"
      ]
  },
  {
      "name": "Deep Learning",
      "trans": [
          "深度学习"
      ]
  },
  {
      "name": "Deep Neural Network",
      "trans": [
          "深度神经网络"
      ]
  },
  {
      "name": "Deep Q-Network",
      "trans": [
          "深度Q网络"
      ]
  },
  {
      "name": "Delta-Bar-Delta",
      "trans": [
          "Delta-Bar-Delta"
      ]
  },
  {
      "name": "Denoising",
      "trans": [
          "去噪"
      ]
  },
  {
      "name": "Denoising Autoencoder",
      "trans": [
          "去噪自编码器"
      ]
  },
  {
      "name": "Denoising Score Matching",
      "trans": [
          "去躁分数匹配"
      ]
  },
  {
      "name": "Density Estimation",
      "trans": [
          "密度估计"
      ]
  },
  {
      "name": "Density-Based Clustering",
      "trans": [
          "密度聚类"
      ]
  },
  {
      "name": "Derivative",
      "trans": [
          "导数"
      ]
  },
  {
      "name": "Determinant",
      "trans": [
          "行列式"
      ]
  },
  {
      "name": "Diagonal Matrix",
      "trans": [
          "对角矩阵"
      ]
  },
  {
      "name": "Dictionary Learning",
      "trans": [
          "字典学习"
      ]
  },
  {
      "name": "Dimension Reduction",
      "trans": [
          "降维"
      ]
  },
  {
      "name": "Directed Edge",
      "trans": [
          "有向边"
      ]
  },
  {
      "name": "Directed Graphical Model",
      "trans": [
          "有向图模型"
      ]
  },
  {
      "name": "Directed Separation",
      "trans": [
          "有向分离"
      ]
  },
  {
      "name": "Dirichlet Distribution",
      "trans": [
          "狄利克雷分布"
      ]
  },
  {
      "name": "Discriminative Model",
      "trans": [
          "判别式模型"
      ]
  },
  {
      "name": "Discriminator",
      "trans": [
          "判别器"
      ]
  },
  {
      "name": "Discriminator Network",
      "trans": [
          "判别网络"
      ]
  },
  {
      "name": "Distance Measure",
      "trans": [
          "距离度量"
      ]
  },
  {
      "name": "Distance Metric Learning",
      "trans": [
          "距离度量学习"
      ]
  },
  {
      "name": "Distributed Representation",
      "trans": [
          "分布式表示"
      ]
  },
  {
      "name": "Diverge",
      "trans": [
          "发散"
      ]
  },
  {
      "name": "Divergence",
      "trans": [
          "散度"
      ]
  },
  {
      "name": "Diversity",
      "trans": [
          "多样性"
      ]
  },
  {
      "name": "Diversity Measure",
      "trans": [
          "多样性度量/差异性度量"
      ]
  },
  {
      "name": "Domain Adaptation",
      "trans": [
          "领域自适应"
      ]
  },
  {
      "name": "Dominant Eigenvalue",
      "trans": [
          "主特征值"
      ]
  },
  {
      "name": "Dominant Strategy",
      "trans": [
          "占优策略"
      ]
  },
  {
      "name": "Down Sampling",
      "trans": [
          "下采样"
      ]
  },
  {
      "name": "Dropout",
      "trans": [
          "暂退法"
      ]
  },
  {
      "name": "Dropout Boosting",
      "trans": [
          "暂退Boosting"
      ]
  },
  {
      "name": "Dropout Method",
      "trans": [
          "暂退法"
      ]
  },
  {
      "name": "Dual Problem",
      "trans": [
          "对偶问题"
      ]
  },
  {
      "name": "Dummy Node",
      "trans": [
          "哑结点"
      ]
  },
  {
      "name": "Dynamic Bayesian Network",
      "trans": [
          "动态贝叶斯网络"
      ]
  },
  {
      "name": "Dynamic Programming",
      "trans": [
          "动态规划"
      ]
  },
  {
      "name": "Early Stopping",
      "trans": [
          "早停"
      ]
  },
  {
      "name": "Eigendecomposition",
      "trans": [
          "特征分解"
      ]
  },
  {
      "name": "Eigenvalue",
      "trans": [
          "特征值"
      ]
  },
  {
      "name": "Element-Wise Product",
      "trans": [
          "逐元素积"
      ]
  },
  {
      "name": "Embedding",
      "trans": [
          "嵌入"
      ]
  },
  {
      "name": "Empirical Conditional Entropy",
      "trans": [
          "经验条件熵"
      ]
  },
  {
      "name": "Empirical Distribution",
      "trans": [
          "经验分布"
      ]
  },
  {
      "name": "Empirical Entropy",
      "trans": [
          "经验熵"
      ]
  },
  {
      "name": "Empirical Error",
      "trans": [
          "经验误差"
      ]
  },
  {
      "name": "Empirical Risk",
      "trans": [
          "经验风险"
      ]
  },
  {
      "name": "Empirical Risk Minimization",
      "trans": [
          "经验风险最小化"
      ]
  },
  {
      "name": "Encoder",
      "trans": [
          "编码器"
      ]
  },
  {
      "name": "Encoding",
      "trans": [
          "编码"
      ]
  },
  {
      "name": "End-To-End",
      "trans": [
          "端到端"
      ]
  },
  {
      "name": "Energy Function",
      "trans": [
          "能量函数"
      ]
  },
  {
      "name": "Energy-Based Model",
      "trans": [
          "基于能量的模型"
      ]
  },
  {
      "name": "Ensemble Learning",
      "trans": [
          "集成学习"
      ]
  },
  {
      "name": "Ensemble Pruning",
      "trans": [
          "集成修剪"
      ]
  },
  {
      "name": "Entropy",
      "trans": [
          "熵"
      ]
  },
  {
      "name": "Episode",
      "trans": [
          "回合"
      ]
  },
  {
      "name": "Epoch",
      "trans": [
          "轮"
      ]
  },
  {
      "name": "Error",
      "trans": [
          "误差"
      ]
  },
  {
      "name": "Error Backpropagation Algorithm",
      "trans": [
          "误差反向传播算法"
      ]
  },
  {
      "name": "Error Backpropagation",
      "trans": [
          "误差反向传播"
      ]
  },
  {
      "name": "Error Correcting Output Codes",
      "trans": [
          "纠错输出编码"
      ]
  },
  {
      "name": "Error Rate",
      "trans": [
          "错误率"
      ]
  },
  {
      "name": "Error-Ambiguity Decomposition",
      "trans": [
          "误差－分歧分解"
      ]
  },
  {
      "name": "Estimator",
      "trans": [
          "估计/估计量"
      ]
  },
  {
      "name": "Euclidean Distance",
      "trans": [
          "欧氏距离"
      ]
  },
  {
      "name": "Evidence",
      "trans": [
          "证据"
      ]
  },
  {
      "name": "Evidence Lower Bound",
      "trans": [
          "证据下界"
      ]
  },
  {
      "name": "Exact Inference",
      "trans": [
          "精确推断"
      ]
  },
  {
      "name": "Example",
      "trans": [
          "样例"
      ]
  },
  {
      "name": "Expectation",
      "trans": [
          "期望"
      ]
  },
  {
      "name": "Expectation Maximization",
      "trans": [
          "期望最大化"
      ]
  },
  {
      "name": "Expected Loss",
      "trans": [
          "期望损失"
      ]
  },
  {
      "name": "Expert System",
      "trans": [
          "专家系统"
      ]
  },
  {
      "name": "Exploding Gradient",
      "trans": [
          "梯度爆炸"
      ]
  },
  {
      "name": "Exponential Loss Function",
      "trans": [
          "指数损失函数"
      ]
  },
  {
      "name": "Factor",
      "trans": [
          "因子"
      ]
  },
  {
      "name": "Factorization",
      "trans": [
          "因子分解"
      ]
  },
  {
      "name": "Feature",
      "trans": [
          "特征"
      ]
  },
  {
      "name": "Feature Engineering",
      "trans": [
          "特征工程"
      ]
  },
  {
      "name": "Feature Map",
      "trans": [
          "特征图"
      ]
  },
  {
      "name": "Feature Selection",
      "trans": [
          "特征选择"
      ]
  },
  {
      "name": "Feature Vector",
      "trans": [
          "特征向量"
      ]
  },
  {
      "name": "Featured Learning",
      "trans": [
          "特征学习"
      ]
  },
  {
      "name": "Feedforward",
      "trans": [
          "前馈"
      ]
  },
  {
      "name": "Feedforward Neural Network",
      "trans": [
          "前馈神经网络"
      ]
  },
  {
      "name": "Few-Shot Learning",
      "trans": [
          "少试学习"
      ]
  },
  {
      "name": "Filter",
      "trans": [
          "滤波器"
      ]
  },
  {
      "name": "Fine-Tuning",
      "trans": [
          "微调"
      ]
  },
  {
      "name": "Fluctuation",
      "trans": [
          "振荡"
      ]
  },
  {
      "name": "Forget Gate",
      "trans": [
          "遗忘门"
      ]
  },
  {
      "name": "Forward Propagation",
      "trans": [
          "前向传播/正向传播"
      ]
  },
  {
      "name": "Forward Stagewise Algorithm",
      "trans": [
          "前向分步算法"
      ]
  },
  {
      "name": "Fractionally Strided Convolution",
      "trans": [
          "微步卷积"
      ]
  },
  {
      "name": "Frobenius Norm",
      "trans": [
          "Frobenius 范数"
      ]
  },
  {
      "name": "Full Padding",
      "trans": [
          "全填充"
      ]
  },
  {
      "name": "Functional",
      "trans": [
          "泛函"
      ]
  },
  {
      "name": "Functional Neuron",
      "trans": [
          "功能神经元"
      ]
  },
  {
      "name": "Gated Recurrent Unit",
      "trans": [
          "门控循环单元"
      ]
  },
  {
      "name": "Gated RNN",
      "trans": [
          "门控RNN"
      ]
  },
  {
      "name": "Gaussian Distribution",
      "trans": [
          "高斯分布"
      ]
  },
  {
      "name": "Gaussian Kernel",
      "trans": [
          "高斯核"
      ]
  },
  {
      "name": "Gaussian Kernel Function",
      "trans": [
          "高斯核函数"
      ]
  },
  {
      "name": "Gaussian Mixture Model",
      "trans": [
          "高斯混合模型"
      ]
  },
  {
      "name": "Gaussian Process",
      "trans": [
          "高斯过程"
      ]
  },
  {
      "name": "Generalization Ability",
      "trans": [
          "泛化能力"
      ]
  },
  {
      "name": "Generalization Error",
      "trans": [
          "泛化误差"
      ]
  },
  {
      "name": "Generalization Error Bound",
      "trans": [
          "泛化误差上界"
      ]
  },
  {
      "name": "Generalize",
      "trans": [
          "泛化"
      ]
  },
  {
      "name": "Generalized Lagrange Function",
      "trans": [
          "广义拉格朗日函数"
      ]
  },
  {
      "name": "Generalized Linear Model",
      "trans": [
          "广义线性模型"
      ]
  },
  {
      "name": "Generalized Rayleigh Quotient",
      "trans": [
          "广义瑞利商"
      ]
  },
  {
      "name": "Generative Adversarial Network",
      "trans": [
          "生成对抗网络"
      ]
  },
  {
      "name": "Generative Model",
      "trans": [
          "生成式模型"
      ]
  },
  {
      "name": "Generator",
      "trans": [
          "生成器"
      ]
  },
  {
      "name": "Generator Network",
      "trans": [
          "生成器网络"
      ]
  },
  {
      "name": "Genetic Algorithm",
      "trans": [
          "遗传算法"
      ]
  },
  {
      "name": "Gibbs Distribution",
      "trans": [
          "吉布斯分布"
      ]
  },
  {
      "name": "Gibbs Sampling",
      "trans": [
          "吉布斯采样/吉布斯抽样"
      ]
  },
  {
      "name": "Gini Index",
      "trans": [
          "基尼指数"
      ]
  },
  {
      "name": "Global Markov Property",
      "trans": [
          "全局马尔可夫性"
      ]
  },
  {
      "name": "Global Minimum",
      "trans": [
          "全局最小"
      ]
  },
  {
      "name": "Gradient",
      "trans": [
          "梯度"
      ]
  },
  {
      "name": "Gradient Clipping",
      "trans": [
          "梯度截断"
      ]
  },
  {
      "name": "Gradient Descent",
      "trans": [
          "梯度下降"
      ]
  },
  {
      "name": "Gradient Descent Method",
      "trans": [
          "梯度下降法"
      ]
  },
  {
      "name": "Gradient Exploding Problem",
      "trans": [
          "梯度爆炸问题"
      ]
  },
  {
      "name": "Gram Matrix",
      "trans": [
          "Gram 矩阵"
      ]
  },
  {
      "name": "Graph Convolutional Network",
      "trans": [
          "图卷积神经网络/图卷积网络"
      ]
  },
  {
      "name": "Graph Neural Network",
      "trans": [
          "图神经网络"
      ]
  },
  {
      "name": "Graphical Model",
      "trans": [
          "图模型"
      ]
  },
  {
      "name": "Grid Search",
      "trans": [
          "网格搜索"
      ]
  },
  {
      "name": "Ground Truth",
      "trans": [
          "真实值"
      ]
  },
  {
      "name": "Hadamard Product",
      "trans": [
          "Hadamard积"
      ]
  },
  {
      "name": "Hamming Distance",
      "trans": [
          "汉明距离"
      ]
  },
  {
      "name": "Hard Margin",
      "trans": [
          "硬间隔"
      ]
  },
  {
      "name": "Hebbian Rule",
      "trans": [
          "赫布法则"
      ]
  },
  {
      "name": "Hidden Layer",
      "trans": [
          "隐藏层"
      ]
  },
  {
      "name": "Hidden Markov Model",
      "trans": [
          "隐马尔可夫模型"
      ]
  },
  {
      "name": "Hidden Variable",
      "trans": [
          "隐变量"
      ]
  },
  {
      "name": "Hierarchical Clustering",
      "trans": [
          "层次聚类"
      ]
  },
  {
      "name": "Hilbert Space",
      "trans": [
          "希尔伯特空间"
      ]
  },
  {
      "name": "Hinge Loss Function",
      "trans": [
          "合页损失函数/Hinge损失函数"
      ]
  },
  {
      "name": "Hold-Out",
      "trans": [
          "留出法"
      ]
  },
  {
      "name": "Hyperparameter",
      "trans": [
          "超参数"
      ]
  },
  {
      "name": "Hyperparameter Optimization",
      "trans": [
          "超参数优化"
      ]
  },
  {
      "name": "Hypothesis",
      "trans": [
          "假设"
      ]
  },
  {
      "name": "Hypothesis Space",
      "trans": [
          "假设空间"
      ]
  },
  {
      "name": "Hypothesis Test",
      "trans": [
          "假设检验"
      ]
  },
  {
      "name": "Identity Matrix",
      "trans": [
          "单位矩阵"
      ]
  },
  {
      "name": "Imitation Learning",
      "trans": [
          "模仿学习"
      ]
  },
  {
      "name": "Importance Sampling",
      "trans": [
          "重要性采样"
      ]
  },
  {
      "name": "Improved Iterative Scaling",
      "trans": [
          "改进的迭代尺度法"
      ]
  },
  {
      "name": "Incremental Learning",
      "trans": [
          "增量学习"
      ]
  },
  {
      "name": "Independent and Identically Distributed",
      "trans": [
          "独立同分布"
      ]
  },
  {
      "name": "Indicator Function",
      "trans": [
          "指示函数"
      ]
  },
  {
      "name": "Individual Learner",
      "trans": [
          "个体学习器"
      ]
  },
  {
      "name": "Induction",
      "trans": [
          "归纳"
      ]
  },
  {
      "name": "Inductive Bias",
      "trans": [
          "归纳偏好"
      ]
  },
  {
      "name": "Inductive Learning",
      "trans": [
          "归纳学习"
      ]
  },
  {
      "name": "Inductive Logic Programming",
      "trans": [
          "归纳逻辑程序设计"
      ]
  },
  {
      "name": "Inference",
      "trans": [
          "推断"
      ]
  },
  {
      "name": "Information Entropy",
      "trans": [
          "信息熵"
      ]
  },
  {
      "name": "Information Gain",
      "trans": [
          "信息增益"
      ]
  },
  {
      "name": "Inner Product",
      "trans": [
          "内积"
      ]
  },
  {
      "name": "Instance",
      "trans": [
          "示例"
      ]
  },
  {
      "name": "Internal Covariate Shift",
      "trans": [
          "内部协变量偏移"
      ]
  },
  {
      "name": "Inverse Matrix",
      "trans": [
          "逆矩阵"
      ]
  },
  {
      "name": "Inverse Resolution",
      "trans": [
          "逆归结"
      ]
  },
  {
      "name": "Isometric Mapping",
      "trans": [
          "等度量映射"
      ]
  },
  {
      "name": "Jacobian Matrix",
      "trans": [
          "雅可比矩阵"
      ]
  },
  {
      "name": "Jensen Inequality",
      "trans": [
          "Jensen不等式"
      ]
  },
  {
      "name": "Joint Probability Distribution",
      "trans": [
          "联合概率分布"
      ]
  },
  {
      "name": "K-Armed Bandit Problem",
      "trans": [
          "k-摇臂老虎机"
      ]
  },
  {
      "name": "K-Fold Cross Validation",
      "trans": [
          "k 折交叉验证"
      ]
  },
  {
      "name": "Karush-Kuhn-Tucker Condition",
      "trans": [
          "KKT条件"
      ]
  },
  {
      "name": "Karush–Kuhn–Tucker",
      "trans": [
          "Karush–Kuhn–Tucker"
      ]
  },
  {
      "name": "Kernel Function",
      "trans": [
          "核函数"
      ]
  },
  {
      "name": "Kernel Method",
      "trans": [
          "核方法"
      ]
  },
  {
      "name": "Kernel Trick",
      "trans": [
          "核技巧"
      ]
  },
  {
      "name": "Kernelized Linear Discriminant Analysis",
      "trans": [
          "核线性判别分析"
      ]
  },
  {
      "name": "KL Divergence",
      "trans": [
          "KL散度"
      ]
  },
  {
      "name": "L-BFGS",
      "trans": [
          "L-BFGS"
      ]
  },
  {
      "name": "Label",
      "trans": [
          "标签/标记"
      ]
  },
  {
      "name": "Label Space",
      "trans": [
          "标记空间"
      ]
  },
  {
      "name": "Lagrange Duality",
      "trans": [
          "拉格朗日对偶性"
      ]
  },
  {
      "name": "Lagrange Multiplier",
      "trans": [
          "拉格朗日乘子"
      ]
  },
  {
      "name": "Language Model",
      "trans": [
          "语言模型"
      ]
  },
  {
      "name": "Laplace Smoothing",
      "trans": [
          "拉普拉斯平滑"
      ]
  },
  {
      "name": "Laplacian Correction",
      "trans": [
          "拉普拉斯修正"
      ]
  },
  {
      "name": "Latent Dirichlet Allocation",
      "trans": [
          "潜在狄利克雷分配"
      ]
  },
  {
      "name": "Latent Semantic Analysis",
      "trans": [
          "潜在语义分析"
      ]
  },
  {
      "name": "Latent Variable",
      "trans": [
          "潜变量/隐变量"
      ]
  },
  {
      "name": "Law of Large Numbers",
      "trans": [
          "大数定律"
      ]
  },
  {
      "name": "Layer Normalization",
      "trans": [
          "层规范化"
      ]
  },
  {
      "name": "Lazy Learning",
      "trans": [
          "懒惰学习"
      ]
  },
  {
      "name": "Leaky Relu",
      "trans": [
          "泄漏修正线性单元/泄漏整流线性单元"
      ]
  },
  {
      "name": "Learner",
      "trans": [
          "学习器"
      ]
  },
  {
      "name": "Learning",
      "trans": [
          "学习"
      ]
  },
  {
      "name": "Learning By Analogy",
      "trans": [
          "类比学习"
      ]
  },
  {
      "name": "Learning Rate",
      "trans": [
          "学习率"
      ]
  },
  {
      "name": "Learning Vector Quantization",
      "trans": [
          "学习向量量化"
      ]
  },
  {
      "name": "Least Square Method",
      "trans": [
          "最小二乘法"
      ]
  },
  {
      "name": "Least Squares Regression Tree",
      "trans": [
          "最小二乘回归树"
      ]
  },
  {
      "name": "Left Singular Vector",
      "trans": [
          "左奇异向量"
      ]
  },
  {
      "name": "Likelihood",
      "trans": [
          "似然"
      ]
  },
  {
      "name": "Linear Chain Conditional Random Field",
      "trans": [
          "线性链条件随机场"
      ]
  },
  {
      "name": "Linear Classification Model",
      "trans": [
          "线性分类模型"
      ]
  },
  {
      "name": "Linear Classifier",
      "trans": [
          "线性分类器"
      ]
  },
  {
      "name": "Linear Dependence",
      "trans": [
          "线性相关"
      ]
  },
  {
      "name": "Linear Discriminant Analysis",
      "trans": [
          "线性判别分析"
      ]
  },
  {
      "name": "Linear Model",
      "trans": [
          "线性模型"
      ]
  },
  {
      "name": "Linear Regression",
      "trans": [
          "线性回归"
      ]
  },
  {
      "name": "Link Function",
      "trans": [
          "联系函数"
      ]
  },
  {
      "name": "Local Markov Property",
      "trans": [
          "局部马尔可夫性"
      ]
  },
  {
      "name": "Local Minima",
      "trans": [
          "局部极小"
      ]
  },
  {
      "name": "Local Minimum",
      "trans": [
          "局部极小"
      ]
  },
  {
      "name": "Local Representation",
      "trans": [
          "局部式表示/局部式表征"
      ]
  },
  {
      "name": "Log Likelihood",
      "trans": [
          "对数似然函数"
      ]
  },
  {
      "name": "Log Linear Model",
      "trans": [
          "对数线性模型"
      ]
  },
  {
      "name": "Log-Likelihood",
      "trans": [
          "对数似然"
      ]
  },
  {
      "name": "Log-Linear Regression",
      "trans": [
          "对数线性回归"
      ]
  },
  {
      "name": "Logistic Function",
      "trans": [
          "对数几率函数"
      ]
  },
  {
      "name": "Logistic Regression",
      "trans": [
          "对数几率回归"
      ]
  },
  {
      "name": "Logit",
      "trans": [
          "对数几率"
      ]
  },
  {
      "name": "Long Short Term Memory",
      "trans": [
          "长短期记忆"
      ]
  },
  {
      "name": "Long Short-Term Memory Network",
      "trans": [
          "长短期记忆网络"
      ]
  },
  {
      "name": "Loopy Belief Propagation",
      "trans": [
          "环状信念传播"
      ]
  },
  {
      "name": "Loss Function",
      "trans": [
          "损失函数"
      ]
  },
  {
      "name": "Low Rank Matrix Approximation",
      "trans": [
          "低秩矩阵近似"
      ]
  },
  {
      "name": "Machine Learning",
      "trans": [
          "机器学习"
      ]
  },
  {
      "name": "Macron-R",
      "trans": [
          "宏查全率"
      ]
  },
  {
      "name": "Manhattan Distance",
      "trans": [
          "曼哈顿距离"
      ]
  },
  {
      "name": "Manifold",
      "trans": [
          "流形"
      ]
  },
  {
      "name": "Manifold Assumption",
      "trans": [
          "流形假设"
      ]
  },
  {
      "name": "Manifold Learning",
      "trans": [
          "流形学习"
      ]
  },
  {
      "name": "Margin",
      "trans": [
          "间隔"
      ]
  },
  {
      "name": "Marginal Distribution",
      "trans": [
          "边缘分布"
      ]
  },
  {
      "name": "Marginal Independence",
      "trans": [
          "边缘独立性"
      ]
  },
  {
      "name": "Marginalization",
      "trans": [
          "边缘化"
      ]
  },
  {
      "name": "Markov Chain",
      "trans": [
          "马尔可夫链"
      ]
  },
  {
      "name": "Markov Chain Monte Carlo",
      "trans": [
          "马尔可夫链蒙特卡罗"
      ]
  },
  {
      "name": "Markov Decision Process",
      "trans": [
          "马尔可夫决策过程"
      ]
  },
  {
      "name": "Markov Network",
      "trans": [
          "马尔可夫网络"
      ]
  },
  {
      "name": "Markov Process",
      "trans": [
          "马尔可夫过程"
      ]
  },
  {
      "name": "Markov Random Field",
      "trans": [
          "马尔可夫随机场"
      ]
  },
  {
      "name": "Mask",
      "trans": [
          "掩码"
      ]
  },
  {
      "name": "Matrix",
      "trans": [
          "矩阵"
      ]
  },
  {
      "name": "Matrix Inversion",
      "trans": [
          "逆矩阵"
      ]
  },
  {
      "name": "Max Pooling",
      "trans": [
          "最大汇聚"
      ]
  },
  {
      "name": "Maximal Clique",
      "trans": [
          "最大团"
      ]
  },
  {
      "name": "Maximum Entropy Model",
      "trans": [
          "最大熵模型"
      ]
  },
  {
      "name": "Maximum Likelihood Estimation",
      "trans": [
          "极大似然估计"
      ]
  },
  {
      "name": "Maximum Margin",
      "trans": [
          "最大间隔"
      ]
  },
  {
      "name": "Mean Filed",
      "trans": [
          "平均场"
      ]
  },
  {
      "name": "Mean Pooling",
      "trans": [
          "平均汇聚"
      ]
  },
  {
      "name": "Mean Squared Error",
      "trans": [
          "均方误差"
      ]
  },
  {
      "name": "Mean-Field",
      "trans": [
          "平均场"
      ]
  },
  {
      "name": "Memory Network",
      "trans": [
          "记忆网络"
      ]
  },
  {
      "name": "Message Passing",
      "trans": [
          "消息传递"
      ]
  },
  {
      "name": "Metric Learning",
      "trans": [
          "度量学习"
      ]
  },
  {
      "name": "Micro-R",
      "trans": [
          "微查全率"
      ]
  },
  {
      "name": "Minibatch",
      "trans": [
          "小批量"
      ]
  },
  {
      "name": "Minimal Description Length",
      "trans": [
          "最小描述长度"
      ]
  },
  {
      "name": "Minimax Game",
      "trans": [
          "极小极大博弈"
      ]
  },
  {
      "name": "Minkowski Distance",
      "trans": [
          "闵可夫斯基距离"
      ]
  },
  {
      "name": "Mixture of Experts",
      "trans": [
          "混合专家模型"
      ]
  },
  {
      "name": "Mixture-of-Gaussian",
      "trans": [
          "高斯混合"
      ]
  },
  {
      "name": "Model",
      "trans": [
          "模型"
      ]
  },
  {
      "name": "Model Selection",
      "trans": [
          "模型选择"
      ]
  },
  {
      "name": "Momentum Method",
      "trans": [
          "动量法"
      ]
  },
  {
      "name": "Monte Carlo Method",
      "trans": [
          "蒙特卡罗方法"
      ]
  },
  {
      "name": "Moral Graph",
      "trans": [
          "端正图/道德图"
      ]
  },
  {
      "name": "Moralization",
      "trans": [
          "道德化"
      ]
  },
  {
      "name": "Multi-Class Classification",
      "trans": [
          "多分类"
      ]
  },
  {
      "name": "Multi-Head Attention",
      "trans": [
          "多头注意力"
      ]
  },
  {
      "name": "Multi-Head Self-Attention",
      "trans": [
          "多头自注意力"
      ]
  },
  {
      "name": "Multi-Kernel Learning",
      "trans": [
          "多核学习"
      ]
  },
  {
      "name": "Multi-Label Learning",
      "trans": [
          "多标记学习"
      ]
  },
  {
      "name": "Multi-Layer Feedforward Neural Networks",
      "trans": [
          "多层前馈神经网络"
      ]
  },
  {
      "name": "Multi-Layer Perceptron",
      "trans": [
          "多层感知机"
      ]
  },
  {
      "name": "Multinomial Distribution",
      "trans": [
          "多项分布"
      ]
  },
  {
      "name": "Multiple Dimensional Scaling",
      "trans": [
          "多维缩放"
      ]
  },
  {
      "name": "Multiple Linear Regression",
      "trans": [
          "多元线性回归"
      ]
  },
  {
      "name": "Multitask Learning",
      "trans": [
          "多任务学习"
      ]
  },
  {
      "name": "Multivariate Normal Distribution",
      "trans": [
          "多元正态分布"
      ]
  },
  {
      "name": "Mutual Information",
      "trans": [
          "互信息"
      ]
  },
  {
      "name": "N-Gram Model",
      "trans": [
          "N元模型"
      ]
  },
  {
      "name": "Naive Bayes Classifier",
      "trans": [
          "朴素贝叶斯分类器"
      ]
  },
  {
      "name": "Naive Bayes",
      "trans": [
          "朴素贝叶斯"
      ]
  },
  {
      "name": "Nearest Neighbor Classifier",
      "trans": [
          "最近邻分类器"
      ]
  },
  {
      "name": "Negative Log Likelihood",
      "trans": [
          "负对数似然函数"
      ]
  },
  {
      "name": "Neighbourhood Component Analysis",
      "trans": [
          "近邻成分分析"
      ]
  },
  {
      "name": "Net Input",
      "trans": [
          "净输入"
      ]
  },
  {
      "name": "Neural Network",
      "trans": [
          "神经网络"
      ]
  },
  {
      "name": "Neural Turing Machine",
      "trans": [
          "神经图灵机"
      ]
  },
  {
      "name": "Neuron",
      "trans": [
          "神经元"
      ]
  },
  {
      "name": "Newton Method",
      "trans": [
          "牛顿法"
      ]
  },
  {
      "name": "No Free Lunch Theorem",
      "trans": [
          "没有免费午餐定理"
      ]
  },
  {
      "name": "Noise-Contrastive Estimation",
      "trans": [
          "噪声对比估计"
      ]
  },
  {
      "name": "Nominal Attribute",
      "trans": [
          "列名属性"
      ]
  },
  {
      "name": "Non-Convex Optimization",
      "trans": [
          "非凸优化"
      ]
  },
  {
      "name": "Non-Metric Distance",
      "trans": [
          "非度量距离"
      ]
  },
  {
      "name": "Non-Negative Matrix Factorization",
      "trans": [
          "非负矩阵分解"
      ]
  },
  {
      "name": "Non-Ordinal Attribute",
      "trans": [
          "无序属性"
      ]
  },
  {
      "name": "Norm",
      "trans": [
          "范数"
      ]
  },
  {
      "name": "Normal Distribution",
      "trans": [
          "正态分布"
      ]
  },
  {
      "name": "Normalization",
      "trans": [
          "规范化"
      ]
  },
  {
      "name": "Nuclear Norm",
      "trans": [
          "核范数"
      ]
  },
  {
      "name": "Number of Epochs",
      "trans": [
          "轮数"
      ]
  },
  {
      "name": "Numerical Attribute",
      "trans": [
          "数值属性"
      ]
  },
  {
      "name": "Object Detection",
      "trans": [
          "目标检测"
      ]
  },
  {
      "name": "Oblique Decision Tree",
      "trans": [
          "斜决策树"
      ]
  },
  {
      "name": "Occam's Razor",
      "trans": [
          "奥卡姆剃刀"
      ]
  },
  {
      "name": "Odds",
      "trans": [
          "几率"
      ]
  },
  {
      "name": "Off-Policy",
      "trans": [
          "异策略"
      ]
  },
  {
      "name": "On-Policy",
      "trans": [
          "同策略"
      ]
  },
  {
      "name": "One-Shot Learning",
      "trans": [
          "单试学习"
      ]
  },
  {
      "name": "One-Dependent Estimator",
      "trans": [
          "独依赖估计"
      ]
  },
  {
      "name": "One-Hot",
      "trans": [
          "独热"
      ]
  },
  {
      "name": "Online Learning",
      "trans": [
          "在线学习"
      ]
  },
  {
      "name": "Optimizer",
      "trans": [
          "优化器"
      ]
  },
  {
      "name": "Ordinal Attribute",
      "trans": [
          "有序属性"
      ]
  },
  {
      "name": "Orthogonal",
      "trans": [
          "正交"
      ]
  },
  {
      "name": "Orthogonal Matrix",
      "trans": [
          "正交矩阵"
      ]
  },
  {
      "name": "Out-Of-Bag Estimate",
      "trans": [
          "包外估计"
      ]
  },
  {
      "name": "Outlier",
      "trans": [
          "异常点"
      ]
  },
  {
      "name": "Over-Parameterized",
      "trans": [
          "过度参数化"
      ]
  },
  {
      "name": "Overfitting",
      "trans": [
          "过拟合"
      ]
  },
  {
      "name": "Oversampling",
      "trans": [
          "过采样"
      ]
  },
  {
      "name": "Pac-Learnable",
      "trans": [
          "PAC可学习"
      ]
  },
  {
      "name": "Padding",
      "trans": [
          "填充"
      ]
  },
  {
      "name": "Pairwise Markov Property",
      "trans": [
          "成对马尔可夫性"
      ]
  },
  {
      "name": "Parallel Distributed Processing",
      "trans": [
          "分布式并行处理"
      ]
  },
  {
      "name": "Parameter",
      "trans": [
          "参数"
      ]
  },
  {
      "name": "Parameter Estimation",
      "trans": [
          "参数估计"
      ]
  },
  {
      "name": "Parameter Space",
      "trans": [
          "参数空间"
      ]
  },
  {
      "name": "Parameter Tuning",
      "trans": [
          "调参"
      ]
  },
  {
      "name": "Parametric ReLU",
      "trans": [
          "参数化修正线性单元/参数化整流线性单元"
      ]
  },
  {
      "name": "Part-Of-Speech Tagging",
      "trans": [
          "词性标注"
      ]
  },
  {
      "name": "Partial Derivative",
      "trans": [
          "偏导数"
      ]
  },
  {
      "name": "Partially Observable Markov Decision Processes",
      "trans": [
          "部分可观测马尔可夫决策过程"
      ]
  },
  {
      "name": "Partition Function",
      "trans": [
          "配分函数"
      ]
  },
  {
      "name": "Perceptron",
      "trans": [
          "感知机"
      ]
  },
  {
      "name": "Performance Measure",
      "trans": [
          "性能度量"
      ]
  },
  {
      "name": "Perplexity",
      "trans": [
          "困惑度"
      ]
  },
  {
      "name": "Pointer Network",
      "trans": [
          "指针网络"
      ]
  },
  {
      "name": "Policy",
      "trans": [
          "策略"
      ]
  },
  {
      "name": "Policy Gradient",
      "trans": [
          "策略梯度"
      ]
  },
  {
      "name": "Policy Iteration",
      "trans": [
          "策略迭代"
      ]
  },
  {
      "name": "Polynomial Kernel Function",
      "trans": [
          "多项式核函数"
      ]
  },
  {
      "name": "Pooling",
      "trans": [
          "汇聚"
      ]
  },
  {
      "name": "Pooling Layer",
      "trans": [
          "汇聚层"
      ]
  },
  {
      "name": "Positive Definite Matrix",
      "trans": [
          "正定矩阵"
      ]
  },
  {
      "name": "Post-Pruning",
      "trans": [
          "后剪枝"
      ]
  },
  {
      "name": "Potential Function",
      "trans": [
          "势函数"
      ]
  },
  {
      "name": "Power Method",
      "trans": [
          "幂法"
      ]
  },
  {
      "name": "Pre-Training",
      "trans": [
          "预训练"
      ]
  },
  {
      "name": "Precision",
      "trans": [
          "查准率/准确率"
      ]
  },
  {
      "name": "Prepruning",
      "trans": [
          "预剪枝"
      ]
  },
  {
      "name": "Primal Problem",
      "trans": [
          "主问题"
      ]
  },
  {
      "name": "Primary Visual Cortex",
      "trans": [
          "初级视觉皮层"
      ]
  },
  {
      "name": "Principal Component Analysis",
      "trans": [
          "主成分分析"
      ]
  },
  {
      "name": "Prior",
      "trans": [
          "先验"
      ]
  },
  {
      "name": "Probabilistic Context-Free Grammar",
      "trans": [
          "概率上下文无关文法"
      ]
  },
  {
      "name": "Probabilistic Graphical Model",
      "trans": [
          "概率图模型"
      ]
  },
  {
      "name": "Probabilistic Model",
      "trans": [
          "概率模型"
      ]
  },
  {
      "name": "Probability Density Function",
      "trans": [
          "概率密度函数"
      ]
  },
  {
      "name": "Probability Distribution",
      "trans": [
          "概率分布"
      ]
  },
  {
      "name": "Probably Approximately Correct",
      "trans": [
          "概率近似正确"
      ]
  },
  {
      "name": "Proposal Distribution",
      "trans": [
          "提议分布"
      ]
  },
  {
      "name": "Prototype-Based Clustering",
      "trans": [
          "原型聚类"
      ]
  },
  {
      "name": "Proximal Gradient Descent",
      "trans": [
          "近端梯度下降"
      ]
  },
  {
      "name": "Pruning",
      "trans": [
          "剪枝"
      ]
  },
  {
      "name": "Quadratic Loss Function",
      "trans": [
          "平方损失函数"
      ]
  },
  {
      "name": "Quadratic Programming",
      "trans": [
          "二次规划"
      ]
  },
  {
      "name": "Quasi Newton Method",
      "trans": [
          "拟牛顿法"
      ]
  },
  {
      "name": "Radial Basis Function",
      "trans": [
          "径向基函数"
      ]
  },
  {
      "name": "Random Forest",
      "trans": [
          "随机森林"
      ]
  },
  {
      "name": "Random Sampling",
      "trans": [
          "随机采样"
      ]
  },
  {
      "name": "Random Search",
      "trans": [
          "随机搜索"
      ]
  },
  {
      "name": "Random Variable",
      "trans": [
          "随机变量"
      ]
  },
  {
      "name": "Random Walk",
      "trans": [
          "随机游走"
      ]
  },
  {
      "name": "Recall",
      "trans": [
          "查全率/召回率"
      ]
  },
  {
      "name": "Receptive Field",
      "trans": [
          "感受野"
      ]
  },
  {
      "name": "Reconstruction Error",
      "trans": [
          "重构误差"
      ]
  },
  {
      "name": "Rectified Linear Unit",
      "trans": [
          "修正线性单元/整流线性单元"
      ]
  },
  {
      "name": "Recurrent Neural Network",
      "trans": [
          "循环神经网络"
      ]
  },
  {
      "name": "Recursive Neural Network",
      "trans": [
          "递归神经网络"
      ]
  },
  {
      "name": "Regression",
      "trans": [
          "回归"
      ]
  },
  {
      "name": "Regularization",
      "trans": [
          "正则化"
      ]
  },
  {
      "name": "Regularizer",
      "trans": [
          "正则化项"
      ]
  },
  {
      "name": "Reinforcement Learning",
      "trans": [
          "强化学习"
      ]
  },
  {
      "name": "Relative Entropy",
      "trans": [
          "相对熵"
      ]
  },
  {
      "name": "Reparameterization",
      "trans": [
          "再参数化/重参数化"
      ]
  },
  {
      "name": "Representation",
      "trans": [
          "表示"
      ]
  },
  {
      "name": "Representation Learning",
      "trans": [
          "表示学习"
      ]
  },
  {
      "name": "Representer Theorem",
      "trans": [
          "表示定理"
      ]
  },
  {
      "name": "Reproducing Kernel Hilbert Space",
      "trans": [
          "再生核希尔伯特空间"
      ]
  },
  {
      "name": "Rescaling",
      "trans": [
          "再缩放"
      ]
  },
  {
      "name": "Reset Gate",
      "trans": [
          "重置门"
      ]
  },
  {
      "name": "Residual Connection",
      "trans": [
          "残差连接"
      ]
  },
  {
      "name": "Residual Network",
      "trans": [
          "残差网络"
      ]
  },
  {
      "name": "Restricted Boltzmann Machine",
      "trans": [
          "受限玻尔兹曼机"
      ]
  },
  {
      "name": "Reward",
      "trans": [
          "奖励"
      ]
  },
  {
      "name": "Ridge Regression",
      "trans": [
          "岭回归"
      ]
  },
  {
      "name": "Right Singular Vector",
      "trans": [
          "右奇异向量"
      ]
  },
  {
      "name": "Risk",
      "trans": [
          "风险"
      ]
  },
  {
      "name": "Robustness",
      "trans": [
          "稳健性"
      ]
  },
  {
      "name": "Root Node",
      "trans": [
          "根结点"
      ]
  },
  {
      "name": "Rule Learning",
      "trans": [
          "规则学习"
      ]
  },
  {
      "name": "Saddle Point",
      "trans": [
          "鞍点"
      ]
  },
  {
      "name": "Sample",
      "trans": [
          "样本"
      ]
  },
  {
      "name": "Sample Complexity",
      "trans": [
          "样本复杂度"
      ]
  },
  {
      "name": "Sample Space",
      "trans": [
          "样本空间"
      ]
  },
  {
      "name": "Scalar",
      "trans": [
          "标量"
      ]
  },
  {
      "name": "Selective Ensemble",
      "trans": [
          "选择性集成"
      ]
  },
  {
      "name": "Self Information",
      "trans": [
          "自信息"
      ]
  },
  {
      "name": "Self-Attention",
      "trans": [
          "自注意力"
      ]
  },
  {
      "name": "Self-Organizing Map",
      "trans": [
          "自组织映射网"
      ]
  },
  {
      "name": "Self-Training",
      "trans": [
          "自训练"
      ]
  },
  {
      "name": "Semi-Definite Programming",
      "trans": [
          "半正定规划"
      ]
  },
  {
      "name": "Semi-Naive Bayes Classifiers",
      "trans": [
          "半朴素贝叶斯分类器"
      ]
  },
  {
      "name": "Semi-Restricted Boltzmann Machine",
      "trans": [
          "半受限玻尔兹曼机"
      ]
  },
  {
      "name": "Semi-Supervised Clustering",
      "trans": [
          "半监督聚类"
      ]
  },
  {
      "name": "Semi-Supervised Learning",
      "trans": [
          "半监督学习"
      ]
  },
  {
      "name": "Semi-Supervised Support Vector Machine",
      "trans": [
          "半监督支持向量机"
      ]
  },
  {
      "name": "Sentiment Analysis",
      "trans": [
          "情感分析"
      ]
  },
  {
      "name": "Separating Hyperplane",
      "trans": [
          "分离超平面"
      ]
  },
  {
      "name": "Sequential Covering",
      "trans": [
          "序贯覆盖"
      ]
  },
  {
      "name": "Sigmoid Belief Network",
      "trans": [
          "Sigmoid信念网络"
      ]
  },
  {
      "name": "Sigmoid Function",
      "trans": [
          "Sigmoid函数"
      ]
  },
  {
      "name": "Signed Distance",
      "trans": [
          "带符号距离"
      ]
  },
  {
      "name": "Similarity Measure",
      "trans": [
          "相似度度量"
      ]
  },
  {
      "name": "Simulated Annealing",
      "trans": [
          "模拟退火"
      ]
  },
  {
      "name": "Simultaneous Localization And Mapping",
      "trans": [
          "即时定位与地图构建"
      ]
  },
  {
      "name": "Singular Value",
      "trans": [
          "奇异值"
      ]
  },
  {
      "name": "Singular Value Decomposition",
      "trans": [
          "奇异值分解"
      ]
  },
  {
      "name": "Skip-Gram Model",
      "trans": [
          "跳元模型"
      ]
  },
  {
      "name": "Smoothing",
      "trans": [
          "平滑"
      ]
  },
  {
      "name": "Soft Margin",
      "trans": [
          "软间隔"
      ]
  },
  {
      "name": "Soft Margin Maximization",
      "trans": [
          "软间隔最大化"
      ]
  },
  {
      "name": "Softmax",
      "trans": [
          "Softmax/软最大化"
      ]
  },
  {
      "name": "Softmax Function",
      "trans": [
          "Softmax函数/软最大化函数"
      ]
  },
  {
      "name": "Softmax Regression",
      "trans": [
          "Softmax回归/软最大化回归"
      ]
  },
  {
      "name": "Softplus Function",
      "trans": [
          "Softplus函数"
      ]
  },
  {
      "name": "Span",
      "trans": [
          "张成子空间"
      ]
  },
  {
      "name": "Sparse Coding",
      "trans": [
          "稀疏编码"
      ]
  },
  {
      "name": "Sparse Representation",
      "trans": [
          "稀疏表示"
      ]
  },
  {
      "name": "Sparsity",
      "trans": [
          "稀疏性"
      ]
  },
  {
      "name": "Specialization",
      "trans": [
          "特化"
      ]
  },
  {
      "name": "Splitting Variable",
      "trans": [
          "切分变量"
      ]
  },
  {
      "name": "Squashing Function",
      "trans": [
          "挤压函数"
      ]
  },
  {
      "name": "Standard Normal Distribution",
      "trans": [
          "标准正态分布"
      ]
  },
  {
      "name": "State",
      "trans": [
          "状态"
      ]
  },
  {
      "name": "State Value Function",
      "trans": [
          "状态值函数"
      ]
  },
  {
      "name": "State-Action Value Function",
      "trans": [
          "状态-动作值函数"
      ]
  },
  {
      "name": "Stationary Distribution",
      "trans": [
          "平稳分布"
      ]
  },
  {
      "name": "Stationary Point",
      "trans": [
          "驻点"
      ]
  },
  {
      "name": "Statistical Learning",
      "trans": [
          "统计学习"
      ]
  },
  {
      "name": "Steepest Descent",
      "trans": [
          "最速下降法"
      ]
  },
  {
      "name": "Stochastic Gradient Descent",
      "trans": [
          "随机梯度下降"
      ]
  },
  {
      "name": "Stochastic Matrix",
      "trans": [
          "随机矩阵"
      ]
  },
  {
      "name": "Stochastic Process",
      "trans": [
          "随机过程"
      ]
  },
  {
      "name": "Stratified Sampling",
      "trans": [
          "分层采样"
      ]
  },
  {
      "name": "Stride",
      "trans": [
          "步幅"
      ]
  },
  {
      "name": "Structural Risk",
      "trans": [
          "结构风险"
      ]
  },
  {
      "name": "Structural Risk Minimization",
      "trans": [
          "结构风险最小化"
      ]
  },
  {
      "name": "Subsample",
      "trans": [
          "子采样"
      ]
  },
  {
      "name": "Subsampling",
      "trans": [
          "下采样"
      ]
  },
  {
      "name": "Subset Search",
      "trans": [
          "子集搜索"
      ]
  },
  {
      "name": "Subspace",
      "trans": [
          "子空间"
      ]
  },
  {
      "name": "Supervised Learning",
      "trans": [
          "监督学习"
      ]
  },
  {
      "name": "Support Vector",
      "trans": [
          "支持向量"
      ]
  },
  {
      "name": "Support Vector Expansion",
      "trans": [
          "支持向量展式"
      ]
  },
  {
      "name": "Support Vector Machine",
      "trans": [
          "支持向量机"
      ]
  },
  {
      "name": "Surrogat Loss",
      "trans": [
          "替代损失"
      ]
  },
  {
      "name": "Surrogate Function",
      "trans": [
          "替代函数"
      ]
  },
  {
      "name": "Surrogate Loss Function",
      "trans": [
          "代理损失函数"
      ]
  },
  {
      "name": "Symbolism",
      "trans": [
          "符号主义"
      ]
  },
  {
      "name": "Tangent Propagation",
      "trans": [
          "正切传播"
      ]
  },
  {
      "name": "Teacher Forcing",
      "trans": [
          "强制教学"
      ]
  },
  {
      "name": "Temporal-Difference Learning",
      "trans": [
          "时序差分学习"
      ]
  },
  {
      "name": "Tensor",
      "trans": [
          "张量"
      ]
  },
  {
      "name": "Test Error",
      "trans": [
          "测试误差"
      ]
  },
  {
      "name": "Test Sample",
      "trans": [
          "测试样本"
      ]
  },
  {
      "name": "Test Set",
      "trans": [
          "测试集"
      ]
  },
  {
      "name": "Threshold",
      "trans": [
          "阈值"
      ]
  },
  {
      "name": "Threshold Logic Unit",
      "trans": [
          "阈值逻辑单元"
      ]
  },
  {
      "name": "Threshold-Moving",
      "trans": [
          "阈值移动"
      ]
  },
  {
      "name": "Tied Weight",
      "trans": [
          "捆绑权重"
      ]
  },
  {
      "name": "Tikhonov Regularization",
      "trans": [
          "Tikhonov正则化"
      ]
  },
  {
      "name": "Time Delay Neural Network",
      "trans": [
          "时延神经网络"
      ]
  },
  {
      "name": "Time Homogenous Markov Chain",
      "trans": [
          "时间齐次马尔可夫链"
      ]
  },
  {
      "name": "Time Step",
      "trans": [
          "时间步"
      ]
  },
  {
      "name": "Token",
      "trans": [
          "词元"
      ]
  },
  {
      "name": "Tokenize",
      "trans": [
          "词元化"
      ]
  },
  {
      "name": "Tokenization",
      "trans": [
          "词元化"
      ]
  },
  {
      "name": "Tokenizer",
      "trans": [
          "词元分析器"
      ]
  },
  {
      "name": "Topic Model",
      "trans": [
          "话题模型"
      ]
  },
  {
      "name": "Topic Modeling",
      "trans": [
          "话题分析"
      ]
  },
  {
      "name": "Trace",
      "trans": [
          "迹"
      ]
  },
  {
      "name": "Training",
      "trans": [
          "训练"
      ]
  },
  {
      "name": "Training Error",
      "trans": [
          "训练误差"
      ]
  },
  {
      "name": "Training Sample",
      "trans": [
          "训练样本"
      ]
  },
  {
      "name": "Training Set",
      "trans": [
          "训练集"
      ]
  },
  {
      "name": "Transductive Learning",
      "trans": [
          "直推学习"
      ]
  },
  {
      "name": "Transductive Transfer Learning",
      "trans": [
          "直推迁移学习"
      ]
  },
  {
      "name": "Transfer Learning",
      "trans": [
          "迁移学习"
      ]
  },
  {
      "name": "Transformer",
      "trans": [
          "Transformer"
      ]
  },
  {
      "name": "Transformer Model",
      "trans": [
          "Transformer模型"
      ]
  },
  {
      "name": "Transpose",
      "trans": [
          "转置"
      ]
  },
  {
      "name": "Transposed Convolution",
      "trans": [
          "转置卷积"
      ]
  },
  {
      "name": "Trial And Error",
      "trans": [
          "试错"
      ]
  },
  {
      "name": "Trigram",
      "trans": [
          "三元语法"
      ]
  },
  {
      "name": "Turing Machine",
      "trans": [
          "图灵机"
      ]
  },
  {
      "name": "Underfitting",
      "trans": [
          "欠拟合"
      ]
  },
  {
      "name": "Undersampling",
      "trans": [
          "欠采样"
      ]
  },
  {
      "name": "Undirected Graphical Model",
      "trans": [
          "无向图模型"
      ]
  },
  {
      "name": "Uniform Distribution",
      "trans": [
          "均匀分布"
      ]
  },
  {
      "name": "Unigram",
      "trans": [
          "一元语法"
      ]
  },
  {
      "name": "Unit",
      "trans": [
          "单元"
      ]
  },
  {
      "name": "Universal Approximation Theorem",
      "trans": [
          "通用近似定理"
      ]
  },
  {
      "name": "Universal Approximator",
      "trans": [
          "通用近似器"
      ]
  },
  {
      "name": "Universal Function Approximator",
      "trans": [
          "通用函数近似器"
      ]
  },
  {
      "name": "Unknown Token",
      "trans": [
          "未知词元"
      ]
  },
  {
      "name": "Unsupervised Layer-Wise Training",
      "trans": [
          "无监督逐层训练"
      ]
  },
  {
      "name": "Unsupervised Learning",
      "trans": [
          "无监督学习"
      ]
  },
  {
      "name": "Update Gate",
      "trans": [
          "更新门"
      ]
  },
  {
      "name": "Upsampling",
      "trans": [
          "上采样"
      ]
  },
  {
      "name": "V-Structure",
      "trans": [
          "V型结构"
      ]
  },
  {
      "name": "Validation Set",
      "trans": [
          "验证集"
      ]
  },
  {
      "name": "Validity Index",
      "trans": [
          "有效性指标"
      ]
  },
  {
      "name": "Value Function Approximation",
      "trans": [
          "值函数近似"
      ]
  },
  {
      "name": "Value Iteration",
      "trans": [
          "值迭代"
      ]
  },
  {
      "name": "Vanishing Gradient Problem",
      "trans": [
          "梯度消失问题"
      ]
  },
  {
      "name": "Vapnik-Chervonenkis Dimension",
      "trans": [
          "VC维"
      ]
  },
  {
      "name": "Variable Elimination",
      "trans": [
          "变量消去"
      ]
  },
  {
      "name": "Variance",
      "trans": [
          "方差"
      ]
  },
  {
      "name": "Variational Autoencoder",
      "trans": [
          "变分自编码器"
      ]
  },
  {
      "name": "Variational Inference",
      "trans": [
          "变分推断"
      ]
  },
  {
      "name": "Vector",
      "trans": [
          "向量"
      ]
  },
  {
      "name": "Vector Space Model",
      "trans": [
          "向量空间模型"
      ]
  },
  {
      "name": "Version Space",
      "trans": [
          "版本空间"
      ]
  },
  {
      "name": "Viterbi Algorithm",
      "trans": [
          "维特比算法"
      ]
  },
  {
      "name": "Vocabulary",
      "trans": [
          "词表"
      ]
  },
  {
      "name": "Warp",
      "trans": [
          "线程束"
      ]
  },
  {
      "name": "Weak Learner",
      "trans": [
          "弱学习器"
      ]
  },
  {
      "name": "Weakly Supervised Learning",
      "trans": [
          "弱监督学习"
      ]
  },
  {
      "name": "Weight",
      "trans": [
          "权重"
      ]
  },
  {
      "name": "Weight Decay",
      "trans": [
          "权重衰减"
      ]
  },
  {
      "name": "Weight Sharing",
      "trans": [
          "权共享"
      ]
  },
  {
      "name": "Weighted Voting",
      "trans": [
          "加权投票"
      ]
  },
  {
      "name": "Whitening",
      "trans": [
          "白化"
      ]
  },
  {
      "name": "Winner-Take-All",
      "trans": [
          "胜者通吃"
      ]
  },
  {
      "name": "Within-Class Scatter Matrix",
      "trans": [
          "类内散度矩阵"
      ]
  },
  {
      "name": "Word Embedding",
      "trans": [
          "词嵌入"
      ]
  },
  {
      "name": "Word Sense Disambiguation",
      "trans": [
          "词义消歧"
      ]
  },
  {
      "name": "Word Vector",
      "trans": [
          "词向量"
      ]
  },
  {
      "name": "Zero Padding",
      "trans": [
          "零填充"
      ]
  },
  {
      "name": "Zero-Shot Learning",
      "trans": [
          "零试学习"
      ]
  },
  {
      "name": "Zipf's Law",
      "trans": [
          "齐普夫定律"
      ]
  }
]