這是幾位機(jī)器學(xué)習(xí)權(quán)威專家匯總的725個(gè)機(jī)器學(xué)習(xí)術(shù)語(yǔ)表，非常全面了，值得收藏！
| 英文術(shù)語(yǔ) | 中文翻譯 |
|---|---|
| 0-1 Loss Function | 0-1損失函數(shù) |
| Accept-Reject Sampling Method | 接受-拒絕抽樣法/接受-拒絕采樣法 |
| Accumulated Error Backpropagation | 累積誤差反向傳播 |
| Accuracy | 精度 |
| Acquisition Function | 采集函數(shù) |
| Action | 動(dòng)作 |
| Activation Function | 激活函數(shù) |
| Active Learning | 主動(dòng)學(xué)習(xí) |
| Adaptive Bitrate Algorithm | 自適應(yīng)比特率算法 |
| Adaptive Boosting | AdaBoost |
| Adaptive Gradient Algorithm | AdaGrad |
| Adaptive Moment Estimation Algorithm | Adam算法 |
| Adaptive Resonance Theory | 自適應(yīng)諧振理論 |
| Additive Model | 加性模型 |
| Affinity Matrix | 親和矩陣 |
| Agent | 智能體 |
| Algorithm | 算法 |
| Alpha-Beta Pruning | α-β修剪法 |
| Anomaly Detection | 異常檢測(cè) |
| Approximate Inference | 近似推斷 |
| Area Under ROC Curve | AUC |
| Artificial Intelligence | 人工智能 |
| Artificial Neural Network | 人工神經(jīng)網(wǎng)絡(luò) |
| Artificial Neuron | 人工神經(jīng)元 |
| Attention | 注意力 |
| Attention Mechanism | 注意力機(jī)制 |
| Attribute | 屬性 |
| Attribute Space | 屬性空間 |
| Autoencoder | 自編碼器 |
| Automatic Differentiation | 自動(dòng)微分 |
| Autoregressive Model | 自回歸模型 |
| Back Propagation | 反向傳播 |
| Back Propagation Algorithm | 反向傳播算法 |
| Back Propagation Through Time | 隨時(shí)間反向傳播 |
| Backward Induction | 反向歸納 |
| Backward Search | 反向搜索 |
| Bag of words | 詞袋 |
| Bandit | 賭博機(jī)/老虎機(jī) |
| Base Learner | 基學(xué)習(xí)器 |
| Base Learning Algorithm | 基學(xué)習(xí)算法 |
| Baseline | 基準(zhǔn) |
| Batch | 批量 |
| Batch Normalization | 批量規(guī)范化 |
| Bayes Decision Rule | 貝葉斯決策準(zhǔn)則 |
| Bayes Model Averaging | 貝葉斯模型平均 |
| Bayes Optimal Classifier | 貝葉斯最優(yōu)分類器 |
| Bayes' Theorem | 貝葉斯定理 |
| Bayesian Decision Theory | 貝葉斯決策理論 |
| Bayesian Inference | 貝葉斯推斷 |
| Bayesian Learning | 貝葉斯學(xué)習(xí) |
| Bayesian Network | 貝葉斯網(wǎng)/貝葉斯網(wǎng)絡(luò) |
| Bayesian Optimization | 貝葉斯優(yōu)化 |
| Beam Search | 束搜索 |
| Benchmark | 基準(zhǔn) |
| Belief Network | 信念網(wǎng)/信念網(wǎng)絡(luò) |
| Belief Propagation | 信念傳播 |
| Bellman Equation | 貝爾曼方程 |
| Bernoulli Distribution | 伯努利分布 |
| Beta Distribution | 貝塔分布 |
| Between-Class Scatter Matrix | 類間散度矩陣 |
| BFGS | BFGS |
| Bias | 偏差/偏置 |
| Bias In Affine Function | 偏置 |
| Bias In Statistics | 偏差 |
| Bias Shift | 偏置偏移 |
| Bias-Variance Decomposition | 偏差 - 方差分解 |
| Bias-Variance Dilemma | 偏差 - 方差困境 |
| Bidirectional Recurrent Neural Network | 雙向循環(huán)神經(jīng)網(wǎng)絡(luò) |
| Bigram | 二元語(yǔ)法 |
| Bilingual Evaluation Understudy | BLEU |
| Binary Classification | 二分類 |
| Binomial Distribution | 二項(xiàng)分布 |
| Binomial Test | 二項(xiàng)檢驗(yàn) |
| Boltzmann Distribution | 玻爾茲曼分布 |
| Boltzmann machine | 玻爾茲曼機(jī) |
| Boosting | Boosting |
| Bootstrap Aggregating | Bagging |
| Bootstrap Sampling | 自助采樣法 |
| Bootstrapping | 自助法/自舉法 |
| Break-Event Point | 平衡點(diǎn) |
| Bucketing | 分桶 |
| Calculus of Variations | 變分法 |
| Cascade-Correlation | 級(jí)聯(lián)相關(guān) |
| Catastrophic Forgetting | 災(zāi)難性遺忘 |
| Categorical Distribution | 類別分布 |
| Cell | 單元 |
| Chain Rule | 鏈?zhǔn)椒▌t |
| Chebyshev Distance | 切比雪夫距離 |
| Class | 類別 |
| Class-Imbalance | 類別不平衡 |
| Classification | 分類 |
| Classification And Regression Tree | 分類與回歸樹(shù) |
| Classifier | 分類器 |
| Clique | 團(tuán) |
| Cluster | 簇 |
| Cluster Assumption | 聚類假設(shè) |
| Clustering | 聚類 |
| Clustering Ensemble | 聚類集成 |
| Co-Training | 協(xié)同訓(xùn)練 |
| Coding Matrix | 編碼矩陣 |
| Collaborative Filtering | 協(xié)同過(guò)濾 |
| Competitive Learning | 競(jìng)爭(zhēng)型學(xué)習(xí) |
| Comprehensibility | 可解釋性 |
| Computation Graph | 計(jì)算圖 |
| Computational Learning Theory | 計(jì)算學(xué)習(xí)理論 |
| Conditional Entropy | 條件熵 |
| Conditional Probability | 條件概率 |
| Conditional Probability Distribution | 條件概率分布 |
| Conditional Random Field | 條件隨機(jī)場(chǎng) |
| Conditional Risk | 條件風(fēng)險(xiǎn) |
| Confidence | 置信度 |
| Confusion Matrix | 混淆矩陣 |
| Conjugate Distribution | 共軛分布 |
| Connection Weight | 連接權(quán) |
| Connectionism | 連接主義 |
| Consistency | 一致性 |
| Constrained Optimization | 約束優(yōu)化 |
| Context Variable | 上下文變量 |
| Context Vector | 上下文向量 |
| Context Window | 上下文窗口 |
| Context Word | 上下文詞 |
| Contextual Bandit | 上下文賭博機(jī)/上下文老虎機(jī) |
| Contingency Table | 列聯(lián)表 |
| Continuous Attribute | 連續(xù)屬性 |
| Contrastive Divergence | 對(duì)比散度 |
| Convergence | 收斂 |
| Convex Optimization | 凸優(yōu)化 |
| Convex Quadratic Programming | 凸二次規(guī)劃 |
| Convolution | 卷積 |
| Convolutional Kernel | 卷積核 |
| Convolutional Neural Network | 卷積神經(jīng)網(wǎng)絡(luò) |
| Coordinate Descent | 坐標(biāo)下降 |
| Corpus | 語(yǔ)料庫(kù) |
| Correlation Coefficient | 相關(guān)系數(shù) |
| Cosine Similarity | 余弦相似度 |
| Cost | 代價(jià) |
| Cost Curve | 代價(jià)曲線 |
| Cost Function | 代價(jià)函數(shù) |
| Cost Matrix | 代價(jià)矩陣 |
| Cost-Sensitive | 代價(jià)敏感 |
| Covariance | 協(xié)方差 |
| Covariance Matrix | 協(xié)方差矩陣 |
| Critical Point | 臨界點(diǎn) |
| Cross Entropy | 交叉熵 |
| Cross Validation | 交叉驗(yàn)證 |
| Curse of Dimensionality | 維數(shù)災(zāi)難 |
| Cutting Plane Algorithm | 割平面法 |
| Data Mining | 數(shù)據(jù)挖掘 |
| Data Set | 數(shù)據(jù)集 |
| Davidon-Fletcher-Powell | DFP |
| Decision Boundary | 決策邊界 |
| Decision Function | 決策函數(shù) |
| Decision Stump | 決策樹(shù)樁 |
| Decision Tree | 決策樹(shù) |
| Decoder | 解碼器 |
| Decoding | 解碼 |
| Deconvolution | 反卷積 |
| Deconvolutional Network | 反卷積網(wǎng)絡(luò) |
| Deduction | 演繹 |
| Deep Belief Network | 深度信念網(wǎng)絡(luò) |
| Deep Boltzmann Machine | 深度玻爾茲曼機(jī) |
| Deep Convolutional Generative Adversarial Network | 深度卷積生成對(duì)抗網(wǎng)絡(luò) |
| Deep Learning | 深度學(xué)習(xí) |
| Deep Neural Network | 深度神經(jīng)網(wǎng)絡(luò) |
| Deep Q-Network | 深度Q網(wǎng)絡(luò) |
| Delta-Bar-Delta | Delta-Bar-Delta |
| Denoising | 去噪 |
| Denoising Autoencoder | 去噪自編碼器 |
| Denoising Score Matching | 去躁分?jǐn)?shù)匹配 |
| Density Estimation | 密度估計(jì) |
| Density-Based Clustering | 密度聚類 |
| Derivative | 導(dǎo)數(shù) |
| Determinant | 行列式 |
| Diagonal Matrix | 對(duì)角矩陣 |
| Dictionary Learning | 字典學(xué)習(xí) |
| Dimension Reduction | 降維 |
| Directed Edge | 有向邊 |
| Directed Graphical Model | 有向圖模型 |
| Directed Separation | 有向分離 |
| Dirichlet Distribution | 狄利克雷分布 |
| Discriminative Model | 判別式模型 |
| Discriminator | 判別器 |
| Discriminator Network | 判別網(wǎng)絡(luò) |
| Distance Measure | 距離度量 |
| Distance Metric Learning | 距離度量學(xué)習(xí) |
| Distributed Representation | 分布式表示 |
| Diverge | 發(fā)散 |
| Divergence | 散度 |
| Diversity | 多樣性 |
| Diversity Measure | 多樣性度量/差異性度量 |
| Domain Adaptation | 領(lǐng)域自適應(yīng) |
| Dominant Strategy | 主特征值 |
| Dominant Strategy | 占優(yōu)策略 |
| Down Sampling | 下采樣 |
| Dropout | 暫退法 |
| Dropout Boosting | 暫退Boosting |
| Dropout Method | 暫退法 |
| Dual Problem | 對(duì)偶問(wèn)題 |
| Dummy Node | 啞結(jié)點(diǎn) |
| Dynamic Bayesian Network | 動(dòng)態(tài)貝葉斯網(wǎng)絡(luò) |
| Dynamic Programming | 動(dòng)態(tài)規(guī)劃 |
| Early Stopping | 早停 |
| Eigendecomposition | 特征分解 |
| Eigenvalue | 特征值 |
| Element-Wise Product | 逐元素積 |
| Embedding | 嵌入 |
| Empirical Conditional Entropy | 經(jīng)驗(yàn)條件熵 |
| Empirical Distribution | 經(jīng)驗(yàn)分布 |
| Empirical Entropy | 經(jīng)驗(yàn)熵 |
| Empirical Error | 經(jīng)驗(yàn)誤差 |
| Empirical Risk | 經(jīng)驗(yàn)風(fēng)險(xiǎn) |
| Empirical Risk Minimization | 經(jīng)驗(yàn)風(fēng)險(xiǎn)最小化 |
| Encoder | 編碼器 |
| Encoding | 編碼 |
| End-To-End | 端到端 |
| Energy Function | 能量函數(shù) |
| Energy-Based Model | 基于能量的模型 |
| Ensemble Learning | 集成學(xué)習(xí) |
| Ensemble Pruning | 集成修剪 |
| Entropy | 熵 |
| Episode | 回合 |
| Epoch | 輪 |
| Error | 誤差 |
| Error Backpropagation Algorithm | 誤差反向傳播算法 |
| Error Backpropagation | 誤差反向傳播 |
| Error Correcting Output Codes | 糾錯(cuò)輸出編碼 |
| Error Rate | 錯(cuò)誤率 |
| Error-Ambiguity Decomposition | 誤差－分歧分解 |
| Estimator | 估計(jì)/估計(jì)量 |
| Euclidean Distance | 歐氏距離 |
| Evidence | 證據(jù) |
| Evidence Lower Bound | 證據(jù)下界 |
| Exact Inference | 精確推斷 |
| Example | 樣例 |
| Expectation | 期望 |
| Expectation Maximization | 期望最大化 |
| Expected Loss | 期望損失 |
| Expert System | 專家系統(tǒng) |
| Exploding Gradient | 梯度爆炸 |
| Exponential Loss Function | 指數(shù)損失函數(shù) |
| Factor | 因子 |
| Factorization | 因子分解 |
| Feature | 特征 |
| Feature Engineering | 特征工程 |
| Feature Map | 特征圖 |
| Feature Selection | 特征選擇 |
| Feature Vector | 特征向量 |
| Featured Learning | 特征學(xué)習(xí) |
| Feedforward | 前饋 |
| Feedforward Neural Network | 前饋神經(jīng)網(wǎng)絡(luò) |
| Few-Shot Learning | 少試學(xué)習(xí) |
| Filter | 濾波器 |
| Fine-Tuning | 微調(diào) |
| Fluctuation | 振蕩 |
| Forget Gate | 遺忘門 |
| Forward Propagation | 前向傳播/正向傳播 |
| Forward Stagewise Algorithm | 前向分步算法 |
| Fractionally Strided Convolution | 微步卷積 |
| Frobenius Norm | Frobenius 范數(shù) |
| Full Padding | 全填充 |
| Functional | 泛函 |
| Functional Neuron | 功能神經(jīng)元 |
| Gated Recurrent Unit | 門控循環(huán)單元 |
| Gated RNN | 門控RNN |
| Gaussian Distribution | 高斯分布 |
| Gaussian Kernel | 高斯核 |
| Gaussian Kernel Function | 高斯核函數(shù) |
| Gaussian Mixture Model | 高斯混合模型 |
| Gaussian Process | 高斯過(guò)程 |
| Generalization Ability | 泛化能力 |
| Generalization Error | 泛化誤差 |
| Generalization Error Bound | 泛化誤差上界 |
| Generalize | 泛化 |
| Generalized Lagrange Function | 廣義拉格朗日函數(shù) |
| Generalized Linear Model | 廣義線性模型 |
| Generalized Rayleigh Quotient | 廣義瑞利商 |
| Generative Adversarial Network | 生成對(duì)抗網(wǎng)絡(luò) |
| Generative Model | 生成式模型 |
| Generator | 生成器 |
| Generator Network | 生成器網(wǎng)絡(luò) |
| Genetic Algorithm | 遺傳算法 |
| Gibbs Distribution | 吉布斯分布 |
| Gibbs Sampling | 吉布斯采樣/吉布斯抽樣 |
| Gini Index | 基尼指數(shù) |
| Global Markov Property | 全局馬爾可夫性 |
| Global Minimum | 全局最小 |
| Gradient | 梯度 |
| Gradient Clipping | 梯度截?cái)?/td> |
| Gradient Descent | 梯度下降 |
| Gradient Descent Method | 梯度下降法 |
| Gradient Exploding Problem | 梯度爆炸問(wèn)題 |
| Gram Matrix | Gram 矩陣 |
| Graph Convolutional Network | 圖卷積神經(jīng)網(wǎng)絡(luò)/圖卷積網(wǎng)絡(luò) |
| Graph Neural Network | 圖神經(jīng)網(wǎng)絡(luò) |
| Graphical Model | 圖模型 |
| Grid Search | 網(wǎng)格搜索 |
| Ground Truth | 真實(shí)值 |
| Hadamard Product | Hadamard積 |
| Hamming Distance | 漢明距離 |
| Hard Margin | 硬間隔 |
| Hebbian Rule | 赫布法則 |
| Hidden Layer | 隱藏層 |
| Hidden Markov Model | 隱馬爾可夫模型 |
| Hidden Variable | 隱變量 |
| Hierarchical Clustering | 層次聚類 |
| Hilbert Space | 希爾伯特空間 |
| Hinge Loss Function | 合頁(yè)損失函數(shù)/Hinge損失函數(shù) |
| Hold-Out | 留出法 |
| Hyperparameter | 超參數(shù) |
| Hyperparameter Optimization | 超參數(shù)優(yōu)化 |
| Hypothesis | 假設(shè) |
| Hypothesis Space | 假設(shè)空間 |
| Hypothesis Test | 假設(shè)檢驗(yàn) |
| Identity Matrix | 單位矩陣 |
| Imitation Learning | 模仿學(xué)習(xí) |
| Importance Sampling | 重要性采樣 |
| Improved Iterative Scaling | 改進(jìn)的迭代尺度法 |
| Incremental Learning | 增量學(xué)習(xí) |
| Independent and Identically Distributed | 獨(dú)立同分布 |
| Indicator Function | 指示函數(shù) |
| Individual Learner | 個(gè)體學(xué)習(xí)器 |
| Induction | 歸納 |
| Inductive Bias | 歸納偏好 |
| Inductive Learning | 歸納學(xué)習(xí) |
| Inductive Logic Programming | 歸納邏輯程序設(shè)計(jì) |
| Inference | 推斷 |
| Information Entropy | 信息熵 |
| Information Gain | 信息增益 |
| Inner Product | 內(nèi)積 |
| Instance | 示例 |
| Internal Covariate Shift | 內(nèi)部協(xié)變量偏移 |
| Inverse Matrix | 逆矩陣 |
| Inverse Resolution | 逆歸結(jié) |
| Isometric Mapping | 等度量映射 |
| Jacobian Matrix | 雅可比矩陣 |
| Jensen Inequality | Jensen不等式 |
| Joint Probability Distribution | 聯(lián)合概率分布 |
| K-Armed Bandit Problem | k-搖臂老虎機(jī) |
| K-Fold Cross Validation | k 折交叉驗(yàn)證 |
| Karush-Kuhn-Tucker Condition | KKT條件 |
| Karush–Kuhn–Tucker | Karush–Kuhn–Tucker |
| Kernel Function | 核函數(shù) |
| Kernel Method | 核方法 |
| Kernel Trick | 核技巧 |
| Kernelized Linear Discriminant Analysis | 核線性判別分析 |
| KL Divergence | KL散度 |
| L-BFGS | L-BFGS |
| Label | 標(biāo)簽 |
| Label Space | 標(biāo)記空間 |
| Lagrange Duality | 拉格朗日對(duì)偶性 |
| Lagrange Multiplier | 拉格朗日乘子 |
| Language Model | 語(yǔ)言模型 |
| Laplace Smoothing | 拉普拉斯平滑 |
| Laplacian Correction | 拉普拉斯修正 |
| Latent Dirichlet Allocation | 潛在狄利克雷分配 |
| Latent Semantic Analysis | 潛在語(yǔ)義分析 |
| Latent Variable | 潛變量/隱變量 |
| Law of Large Numbers | 大數(shù)定律 |
| Layer Normalization | 層規(guī)范化 |
| Lazy Learning | 懶惰學(xué)習(xí) |
| Leaky Relu | 泄漏修正線性單元/泄漏整流線性單元 |
| Learner | 學(xué)習(xí)器 |
| Learning | 學(xué)習(xí) |
| Learning By Analogy | 類比學(xué)習(xí) |
| Learning Rate | 學(xué)習(xí)率 |
| Learning Vector Quantization | 學(xué)習(xí)向量量化 |
| Least Square Method | 最小二乘法 |
| Least Squares Regression Tree | 最小二乘回歸樹(shù) |
| Left Singular Vector | 左奇異向量 |
| Likelihood | 似然 |
| Linear Chain Conditional Random Field | 線性鏈條件隨機(jī)場(chǎng) |
| Linear Classification Model | 線性分類模型 |
| Linear Classifier | 線性分類器 |
| Linear Dependence | 線性相關(guān) |
| Linear Discriminant Analysis | 線性判別分析 |
| Linear Model | 線性模型 |
| Linear Regression | 線性回歸 |
| Link Function | 聯(lián)系函數(shù) |
| Local Markov Property | 局部馬爾可夫性 |
| Local Minima | 局部極小 |
| Local Minimum | 局部極小 |
| Local Representation | 局部式表示/局部式表征 |
| Log Likelihood | 對(duì)數(shù)似然函數(shù) |
| Log Linear Model | 對(duì)數(shù)線性模型 |
| Log-Likelihood | 對(duì)數(shù)似然 |
| Log-Linear Regression | 對(duì)數(shù)線性回歸 |
| Logistic Function | 對(duì)數(shù)幾率函數(shù) |
| Logistic Regression | 對(duì)數(shù)幾率回歸 |
| Logit | 對(duì)數(shù)幾率 |
| Long Short Term Memory | 長(zhǎng)短期記憶 |
| Long Short-Term Memory Network | 長(zhǎng)短期記憶網(wǎng)絡(luò) |
| Loopy Belief Propagation | 環(huán)狀信念傳播 |
| Loss Function | 損失函數(shù) |
| Low Rank Matrix Approximation | 低秩矩陣近似 |
| Machine Learning | 機(jī)器學(xué)習(xí) |
| Macron-R | 宏查全率 |
| Manhattan Distance | 曼哈頓距離 |
| Manifold | 流形 |
| Manifold Assumption | 流形假設(shè) |
| Manifold Learning | 流形學(xué)習(xí) |
| Margin | 間隔 |
| Marginal Distribution | 邊緣分布 |
| Marginal Independence | 邊緣獨(dú)立性 |
| Marginalization | 邊緣化 |
| Markov Chain | 馬爾可夫鏈 |
| Markov Chain Monte Carlo | 馬爾可夫鏈蒙特卡羅 |
| Markov Decision Process | 馬爾可夫決策過(guò)程 |
| Markov Network | 馬爾可夫網(wǎng)絡(luò) |
| Markov Process | 馬爾可夫過(guò)程 |
| Markov Random Field | 馬爾可夫隨機(jī)場(chǎng) |
| Mask | 掩碼 |
| Matrix | 矩陣 |
| Matrix Inversion | 逆矩陣 |
| Max Pooling | 最大匯聚 |
| Maximal Clique | 最大團(tuán) |
| Maximum Entropy Model | 最大熵模型 |
| Maximum Likelihood Estimation | 極大似然估計(jì) |
| Maximum Margin | 最大間隔 |
| Mean Filed | 平均場(chǎng) |
| Mean Pooling | 平均匯聚 |
| Mean Squared Error | 均方誤差 |
| Mean-Field | 平均場(chǎng) |
| Memory Network | 記憶網(wǎng)絡(luò) |
| Message Passing | 消息傳遞 |
| Metric Learning | 度量學(xué)習(xí) |
| Micro-R | 微查全率 |
| Minibatch | 小批量 |
| Minimal Description Length | 最小描述長(zhǎng)度 |
| Minimax Game | 極小極大博弈 |
| Minkowski Distance | 閔可夫斯基距離 |
| Mixture of Experts | 混合專家模型 |
| Mixture-of-Gaussian | 高斯混合 |
| Model | 模型 |
| Model Selection | 模型選擇 |
| Momentum Method | 動(dòng)量法 |
| Monte Carlo Method | 蒙特卡羅方法 |
| Moral Graph | 端正圖/道德圖 |
| Moralization | 道德化 |
| Multi-Class Classification | 多分類 |
| Multi-Head Attention | 多頭注意力 |
| Multi-Head Self-Attention | 多頭自注意力 |
| Multi-Kernel Learning | 多核學(xué)習(xí) |
| Multi-Label Learning | 多標(biāo)記學(xué)習(xí) |
| Multi-Layer Feedforward Neural Networks | 多層前饋神經(jīng)網(wǎng)絡(luò) |
| Multi-Layer Perceptron | 多層感知機(jī) |
| Multinomial Distribution | 多項(xiàng)分布 |
| Multiple Dimensional Scaling | 多維縮放 |
| Multiple Linear Regression | 多元線性回歸 |
| Multitask Learning | 多任務(wù)學(xué)習(xí) |
| Multivariate Normal Distribution | 多元正態(tài)分布 |
| Mutual Information | 互信息 |
| N-Gram Model | N元模型 |
| Naive Bayes Classifier | 樸素貝葉斯分類器 |
| Naive Bayes | 樸素貝葉斯 |
| Nearest Neighbor Classifier | 最近鄰分類器 |
| Negative Log Likelihood | 負(fù)對(duì)數(shù)似然函數(shù) |
| Neighbourhood Component Analysis | 近鄰成分分析 |
| Net Input | 凈輸入 |
| Neural Network | 神經(jīng)網(wǎng)絡(luò) |
| Neural Turing Machine | 神經(jīng)圖靈機(jī) |
| Neuron | 神經(jīng)元 |
| Newton Method | 牛頓法 |
| No Free Lunch Theorem | 沒(méi)有免費(fèi)午餐定理 |
| Noise-Contrastive Estimation | 噪聲對(duì)比估計(jì) |
| Nominal Attribute | 列名屬性 |
| Non-Convex Optimization | 非凸優(yōu)化 |
| Non-Metric Distance | 非度量距離 |
| Non-Negative Matrix Factorization | 非負(fù)矩陣分解 |
| Non-Ordinal Attribute | 無(wú)序?qū)傩?/td> |
| Norm | 范數(shù) |
| Normal Distribution | 正態(tài)分布 |
| Normalization | 規(guī)范化 |
| Nuclear Norm | 核范數(shù) |
| Number of Epochs | 輪數(shù) |
| Numerical Attribute | 數(shù)值屬性 |
| Object Detection | 目標(biāo)檢測(cè) |
| Oblique Decision Tree | 斜決策樹(shù) |
| Occam's Razor | 奧卡姆剃刀 |
| Odds | 幾率 |
| Off-Policy | 異策略 |
| On-Policy | 同策略 |
| One-Dependent Estimator | 獨(dú)依賴估計(jì) |
| One-Hot | 獨(dú)熱 |
| Online Learning | 在線學(xué)習(xí) |
| Optimizer | 優(yōu)化器 |
| Ordinal Attribute | 有序?qū)傩?/td> |
| Orthogonal | 正交 |
| Orthogonal Matrix | 正交矩陣 |
| Out-Of-Bag Estimate | 包外估計(jì) |
| Outlier | 異常點(diǎn) |
| Over-Parameterized | 過(guò)度參數(shù)化 |
| Overfitting | 過(guò)擬合 |
| Oversampling | 過(guò)采樣 |
| Pac-Learnable | PAC可學(xué)習(xí) |
| Padding | 填充 |
| Pairwise Markov Property | 成對(duì)馬爾可夫性 |
| Parallel Distributed Processing | 分布式并行處理 |
| Parameter | 參數(shù) |
| Parameter Estimation | 參數(shù)估計(jì) |
| Parameter Space | 參數(shù)空間 |
| Parameter Tuning | 調(diào)參 |
| Parametric ReLU | 參數(shù)化修正線性單元/參數(shù)化整流線性單元 |
| Part-Of-Speech Tagging | 詞性標(biāo)注 |
| Partial Derivative | 偏導(dǎo)數(shù) |
| Partially Observable Markov Decision Processes | 部分可觀測(cè)馬爾可夫決策過(guò)程 |
| Partition Function | 配分函數(shù) |
| Perceptron | 感知機(jī) |
| Performance Measure | 性能度量 |
| Perplexity | 困惑度 |
| Pointer Network | 指針網(wǎng)絡(luò) |
| Policy | 策略 |
| Policy Gradient | 策略梯度 |
| Policy Iteration | 策略迭代 |
| Polynomial Kernel Function | 多項(xiàng)式核函數(shù) |
| Pooling | 匯聚 |
| Pooling Layer | 匯聚層 |
| Positive Definite Matrix | 正定矩陣 |
| Post-Pruning | 后剪枝 |
| Potential Function | 勢(shì)函數(shù) |
| Power Method | 冪法 |
| Pre-Training | 預(yù)訓(xùn)練 |
| Precision | 查準(zhǔn)率/準(zhǔn)確率 |
| Prepruning | 預(yù)剪枝 |
| Primal Problem | 主問(wèn)題 |
| Primary Visual Cortex | 初級(jí)視覺(jué)皮層 |
| Principal Component Analysis | 主成分分析 |
| Prior | 先驗(yàn) |
| Probabilistic Context-Free Grammar | 概率上下文無(wú)關(guān)文法 |
| Probabilistic Graphical Model | 概率圖模型 |
| Probabilistic Model | 概率模型 |
| Probability Density Function | 概率密度函數(shù) |
| Probability Distribution | 概率分布 |
| Probably Approximately Correct | 概率近似正確 |
| Proposal Distribution | 提議分布 |
| Prototype-Based Clustering | 原型聚類 |
| Proximal Gradient Descent | 近端梯度下降 |
| Pruning | 剪枝 |
| Quadratic Loss Function | 平方損失函數(shù) |
| Quadratic Programming | 二次規(guī)劃 |
| Quasi Newton Method | 擬牛頓法 |
| Radial Basis Function | 徑向基函數(shù) |
| Random Forest | 隨機(jī)森林 |
| Random Sampling | 隨機(jī)采樣 |
| Random Search | 隨機(jī)搜索 |
| Random Variable | 隨機(jī)變量 |
| Random Walk | 隨機(jī)游走 |
| Recall | 查全率/召回率 |
| Receptive Field | 感受野 |
| Reconstruction Error | 重構(gòu)誤差 |
| Rectified Linear Unit | 修正線性單元/整流線性單元 |
| Recurrent Neural Network | 循環(huán)神經(jīng)網(wǎng)絡(luò) |
| Recursive Neural Network | 遞歸神經(jīng)網(wǎng)絡(luò) |
| Regression | 回歸 |
| Regularization | 正則化 |
| Regularizer | 正則化項(xiàng) |
| Reinforcement Learning | 強(qiáng)化學(xué)習(xí) |
| Relative Entropy | 相對(duì)熵 |
| Reparameterization | 再參數(shù)化/重參數(shù)化 |
| Representation | 表示 |
| Representation Learning | 表示學(xué)習(xí) |
| Representer Theorem | 表示定理 |
| Reproducing Kernel Hilbert Space | 再生核希爾伯特空間 |
| Rescaling | 再縮放 |
| Reset Gate | 重置門 |
| Residual Connection | 殘差連接 |
| Residual Network | 殘差網(wǎng)絡(luò) |
| Restricted Boltzmann Machine | 受限玻爾茲曼機(jī) |
| Reward | 獎(jiǎng)勵(lì) |
| Ridge Regression | 嶺回歸 |
| Right Singular Vector | 右奇異向量 |
| Risk | 風(fēng)險(xiǎn) |
| Robustness | 穩(wěn)健性 |
| Root Node | 根結(jié)點(diǎn) |
| Rule Learning | 規(guī)則學(xué)習(xí) |
| Saddle Point | 鞍點(diǎn) |
| Sample | 樣本 |
| Sample Complexity | 樣本復(fù)雜度 |
| Sample Space | 樣本空間 |
| Scalar | 標(biāo)量 |
| Selective Ensemble | 選擇性集成 |
| Self Information | 自信息 |
| Self-Attention | 自注意力 |
| Self-Organizing Map | 自組織映射網(wǎng) |
| Self-Training | 自訓(xùn)練 |
| Semi-Definite Programming | 半正定規(guī)劃 |
| Semi-Naive Bayes Classifiers | 半樸素貝葉斯分類器 |
| Semi-Restricted Boltzmann Machine | 半受限玻爾茲曼機(jī) |
| Semi-Supervised Clustering | 半監(jiān)督聚類 |
| Semi-Supervised Learning | 半監(jiān)督學(xué)習(xí) |
| Semi-Supervised Support Vector Machine | 半監(jiān)督支持向量機(jī) |
| Sentiment Analysis | 情感分析 |
| Separating Hyperplane | 分離超平面 |
| Sequential Covering | 序貫覆蓋 |
| Sigmoid Belief Network | Sigmoid信念網(wǎng)絡(luò) |
| Sigmoid Function | Sigmoid函數(shù) |
| Signed Distance | 帶符號(hào)距離 |
| Similarity Measure | 相似度度量 |
| Simulated Annealing | 模擬退火 |
| Simultaneous Localization And Mapping | 即時(shí)定位與地圖構(gòu)建 |
| Singular Value | 奇異值 |
| Singular Value Decomposition | 奇異值分解 |
| Skip-Gram Model | 跳元模型 |
| Smoothing | 平滑 |
| Soft Margin | 軟間隔 |
| Soft Margin Maximization | 軟間隔最大化 |
| Softmax | Softmax/軟最大化 |
| Softmax Function | Softmax函數(shù)/軟最大化函數(shù) |
| Softmax Regression | Softmax回歸/軟最大化回歸 |
| Softplus Function | Softplus函數(shù) |
| Span | 張成子空間 |
| Sparse Coding | 稀疏編碼 |
| Sparse Representation | 稀疏表示 |
| Sparsity | 稀疏性 |
| Specialization | 特化 |
| Splitting Variable | 切分變量 |
| Squashing Function | 擠壓函數(shù) |
| Standard Normal Distribution | 標(biāo)準(zhǔn)正態(tài)分布 |
| State | 狀態(tài) |
| State Value Function | 狀態(tài)值函數(shù) |
| State-Action Value Function | 狀態(tài)-動(dòng)作值函數(shù) |
| Stationary Distribution | 平穩(wěn)分布 |
| Stationary Point | 駐點(diǎn) |
| Statistical Learning | 統(tǒng)計(jì)學(xué)習(xí) |
| Steepest Descent | 最速下降法 |
| Stochastic Gradient Descent | 隨機(jī)梯度下降 |
| Stochastic Matrix | 隨機(jī)矩陣 |
| Stochastic Process | 隨機(jī)過(guò)程 |
| Stratified Sampling | 分層采樣 |
| Stride | 步幅 |
| Structural Risk | 結(jié)構(gòu)風(fēng)險(xiǎn) |
| Structural Risk Minimization | 結(jié)構(gòu)風(fēng)險(xiǎn)最小化 |
| Subsample | 子采樣 |
| Subsampling | 下采樣 |
| Subset Search | 子集搜索 |
| Subspace | 子空間 |
| Supervised Learning | 監(jiān)督學(xué)習(xí) |
| Support Vector | 支持向量 |
| Support Vector Expansion | 支持向量展式 |
| Support Vector Machine | 支持向量機(jī) |
| Surrogat Loss | 替代損失 |
| Surrogate Function | 替代函數(shù) |
| Surrogate Loss Function | 代理?yè)p失函數(shù) |
| Symbolism | 符號(hào)主義 |
| Tangent Propagation | 正切傳播 |
| Teacher Forcing | 強(qiáng)制教學(xué) |
| Temporal-Difference Learning | 時(shí)序差分學(xué)習(xí) |
| Tensor | 張量 |
| Test Error | 測(cè)試誤差 |
| Test Sample | 測(cè)試樣本 |
| Test Set | 測(cè)試集 |
| Threshold | 閾值 |
| Threshold Logic Unit | 閾值邏輯單元 |
| Threshold-Moving | 閾值移動(dòng) |
| Tied Weight | 捆綁權(quán)重 |
| Tikhonov Regularization | Tikhonov正則化 |
| Time Delay Neural Network | 時(shí)延神經(jīng)網(wǎng)絡(luò) |
| Time Homogenous Markov Chain | 時(shí)間齊次馬爾可夫鏈 |
| Time Step | 時(shí)間步 |
| Token | 詞元 |
| Token | 詞元 |
| Tokenization | 詞元化 |
| Tokenizer | 詞元分析器 |
| Topic Model | 話題模型 |
| Topic Modeling | 話題分析 |
| Trace | 跡 |
| Training | 訓(xùn)練 |
| Training Error | 訓(xùn)練誤差 |
| Training Sample | 訓(xùn)練樣本 |
| Training Set | 訓(xùn)練集 |
| Transductive Learning | 直推學(xué)習(xí) |
| Transductive Transfer Learning | 直推遷移學(xué)習(xí) |
| Transfer Learning | 遷移學(xué)習(xí) |
| Transformer | Transformer |
| Transformer Model | Transformer模型 |
| Transpose | 轉(zhuǎn)置 |
| Transposed Convolution | 轉(zhuǎn)置卷積 |
| Trial And Error | 試錯(cuò) |
| Trigram | 三元語(yǔ)法 |
| Turing Machine | 圖靈機(jī) |
| Underfitting | 欠擬合 |
| Undersampling | 欠采樣 |
| Undirected Graphical Model | 無(wú)向圖模型 |
| Uniform Distribution | 均勻分布 |
| Unigram | 一元語(yǔ)法 |
| Unit | 單元 |
| Universal Approximation Theorem | 通用近似定理 |
| Universal Approximator | 通用近似器 |
| Universal Function Approximator | 通用函數(shù)近似器 |
| Unknown Token | 未知詞元 |
| Unsupervised Layer-Wise Training | 無(wú)監(jiān)督逐層訓(xùn)練 |
| Unsupervised Learning | 無(wú)監(jiān)督學(xué)習(xí) |
| Update Gate | 更新門 |
| Upsampling | 上采樣 |
| V-Structure | V型結(jié)構(gòu) |
| Validation Set | 驗(yàn)證集 |
| Validity Index | 有效性指標(biāo) |
| Value Function Approximation | 值函數(shù)近似 |
| Value Iteration | 值迭代 |
| Vanishing Gradient Problem | 梯度消失問(wèn)題 |
| Vapnik-Chervonenkis Dimension | VC維 |
| Variable Elimination | 變量消去 |
| Variance | 方差 |
| Variational Autoencoder | 變分自編碼器 |
| Variational Inference | 變分推斷 |
| Vector | 向量 |
| Vector Space Model | 向量空間模型 |
| Version Space | 版本空間 |
| Viterbi Algorithm | 維特比算法 |
| Vocabulary | 詞表 |
| Warp | 線程束 |
| Weak Learner | 弱學(xué)習(xí)器 |
| Weakly Supervised Learning | 弱監(jiān)督學(xué)習(xí) |
| Weight | 權(quán)重 |
| Weight Decay | 權(quán)重衰減 |
| Weight Sharing | 權(quán)共享 |
| Weighted Voting | 加權(quán)投票 |
| Whitening | 白化 |
| Winner-Take-All | 勝者通吃 |
| Within-Class Scatter Matrix | 類內(nèi)散度矩陣 |
| Word Embedding | 詞嵌入 |
| Word Sense Disambiguation | 詞義消歧 |
| Word Vector | 詞向量 |
| Zero Padding | 零填充 |
| Zero-Shot Learning | 零試學(xué)習(xí) |
| Zipf's Law | 齊普夫定律 |
