機器學習專業英語單詞
- [1 ] intensity 強度
- [2 ] Regression 迴歸
- [3 ] Loss function 損失函式
- [4 ] non-convex 非凸函式
- [5 ] neural network 神經網路
- [ ] supervised learning 監督學習
- [ ] regression problem 迴歸問題處理的是連續的問題
- [ ] classification problem 分類問題處理的問題是離散的而不是連續的
迴歸問題和分類問題的區別應該在於 迴歸問題的結果是連續的,分類問題的結果是離散的。 - [ ] discreet value 離散值
- [ ] support vector machines 支援向量機,用來處理分類演算法中輸入的維度不單一的情況(甚至輸入維度為無窮)
- [ ] learning theory 學習理論
- [ ] learning algorithms 學習演算法
- [ ] unsupervised learning 無監督學習
- [ ] gradient descent 梯度下降
- [ ] linear regression 線性迴歸
- [ ] Neural Network 神經網路
- [ ] gradient descent 梯度下降 監督學習的一種演算法,用來擬合的演算法
- [ ] normal equations
- [ ] linear algebra 線性代數 原諒我英語不太好
- [ ] superscript上標
- [ ] exponentiation 指數
- [ ] training set 訓練集合
- [ ] training example 訓練樣本
- [ ] hypothesis 假設,用來表示學習演算法的輸出,叫我們不要太糾結H的意思,因為這只是歷史的慣例
- [ ] LMS algorithm “least mean squares” 最小二乘法演算法
- [ ] batch gradient descent 批量梯度下降,因為每次都會計算 最小擬合的方差,所以運算慢
- [ ] constantly gradient descent 字幕組翻譯成“隨機梯度下降” 我怎麼覺得是“常量梯度下降”也就是梯度下降的運算次數不變,一般比批量梯度下降速度快,但是通常不是那麼準確
- [ ] iterative algorithm 迭代演算法
- [ ] partial derivative 偏導數
- [ ] contour 等高線
- [ ] quadratic function 二元函式
- [ ] locally weighted regression區域性加權迴歸
- [ ] underfitting欠擬合
- [ ] overfitting 過擬合
- [ ] non-parametric learning algorithms 無引數學習演算法
- [ ] parametric learning algorithm 引數學習演算法
[ ] other
[ ] activation 啟用值
- [ ] activation function 啟用函式
- [ ] additive noise 加性噪聲
- [ ] autoencoder 自編碼器
- [ ] Autoencoders 自編碼演算法
- [ ] average firing rate 平均啟用率
- [ ] average sum-of-squares error 均方差
- [ ] backpropagation 後向傳播
- [ ] basis 基
- [ ] basis feature vectors 特徵基向量
- [50 ] batch gradient ascent 批量梯度上升法
- [ ] Bayesian regularization method 貝葉斯規則化方法
- [ ] Bernoulli random variable 伯努利隨機變數
- [ ] bias term 偏置項
- [ ] binary classfication 二元分類
- [ ] class labels 型別標記
- [ ] concatenation 級聯
- [ ] conjugate gradient 共軛梯度
- [ ] contiguous groups 聯通區域
- [ ] convex optimization software 凸優化軟體
- [ ] convolution 卷積
- [ ] cost function 代價函式
- [ ] covariance matrix 協方差矩陣
- [ ] DC component 直流分量
- [ ] decorrelation 去相關
- [ ] degeneracy 退化
- [ ] demensionality reduction 降維
- [ ] derivative 導函式
- [ ] diagonal 對角線
- [ ] diffusion of gradients 梯度的彌散
- [ ] eigenvalue 特徵值
- [ ] eigenvector 特徵向量
- [ ] error term 殘差
- [ ] feature matrix 特徵矩陣
- [ ] feature standardization 特徵標準化
- [ ] feedforward architectures 前饋結構演算法
- [ ] feedforward neural network 前饋神經網路
- [ ] feedforward pass 前饋傳導
- [ ] fine-tuned 微調
- [ ] first-order feature 一階特徵
- [ ] forward pass 前向傳導
- [ ] forward propagation 前向傳播
- [ ] Gaussian prior 高斯先驗概率
- [ ] generative model 生成模型
- [ ] gradient descent 梯度下降
- [ ] Greedy layer-wise training 逐層貪婪訓練方法
- [ ] grouping matrix 分組矩陣
- [ ] Hadamard product 阿達馬乘積
- [ ] Hessian matrix Hessian 矩陣
- [ ] hidden layer 隱含層
- [ ] hidden units 隱藏神經元
- [ ] Hierarchical grouping 層次型分組
- [ ] higher-order features 更高階特徵
- [ ] highly non-convex optimization problem 高度非凸的優化問題
- [ ] histogram 直方圖
- [ ] hyperbolic tangent 雙曲正切函式
- [ ] hypothesis 估值,假設
- [ ] identity activation function 恆等激勵函式
- [ ] IID 獨立同分布
- [ ] illumination 照明
- [100 ] inactive 抑制
- [ ] independent component analysis 獨立成份分析
- [ ] input domains 輸入域
- [ ] input layer 輸入層
- [ ] intensity 亮度/灰度
- [ ] intercept term 截距
- [ ] KL divergence 相對熵
- [ ] KL divergence KL分散度
- [ ] k-Means K-均值
- [ ] learning rate 學習速率
- [ ] least squares 最小二乘法
- [ ] linear correspondence 線性響應
- [ ] linear superposition 線性疊加
- [ ] line-search algorithm 線搜尋演算法
- [ ] local mean subtraction 區域性均值消減
- [ ] local optima 區域性最優解
- [ ] logistic regression 邏輯迴歸
- [ ] loss function 損失函式
- [ ] low-pass filtering 低通濾波
- [ ] magnitude 幅值
- [ ] MAP 極大後驗估計
- [ ] maximum likelihood estimation 極大似然估計
- [ ] mean 平均值
- [ ] MFCC Mel 倒頻係數
- [ ] multi-class classification 多元分類
- [ ] neural networks 神經網路
- [ ] neuron 神經元
- [ ] Newton’s method 牛頓法
- [ ] non-convex function 非凸函式
- [ ] non-linear feature 非線性特徵
- [ ] norm 正規化
- [ ] norm bounded 有界範數
- [ ] norm constrained 範數約束
- [ ] normalization 歸一化
- [ ] numerical roundoff errors 數值舍入誤差
- [ ] numerically checking 數值檢驗
- [ ] numerically reliable 數值計算上穩定
- [ ] object detection 物體檢測
- [ ] objective function 目標函式
- [ ] off-by-one error 缺位錯誤
- [ ] orthogonalization 正交化
- [ ] output layer 輸出層
- [ ] overall cost function 總體代價函式
- [ ] over-complete basis 超完備基
- [ ] over-fitting 過擬合
- [ ] parts of objects 目標的部件
- [ ] part-whole decompostion 部分-整體分解
- [ ] PCA 主元分析
- [ ] penalty term 懲罰因子
- [ ] per-example mean subtraction 逐樣本均值消減
- [150 ] pooling 池化
- [ ] pretrain 預訓練
- [ ] principal components analysis 主成份分析
- [ ] quadratic constraints 二次約束
- [ ] RBMs 受限Boltzman機
- [ ] reconstruction based models 基於重構的模型
- [ ] reconstruction cost 重建代價
- [ ] reconstruction term 重構項
- [ ] redundant 冗餘
- [ ] reflection matrix 反射矩陣
- [ ] regularization 正則化
- [ ] regularization term 正則化項
- [ ] rescaling 縮放
- [ ] robust 魯棒性
- [ ] run 行程
- [ ] second-order feature 二階特徵
- [ ] sigmoid activation function S型激勵函式
- [ ] significant digits 有效數字
- [ ] singular value 奇異值
- [ ] singular vector 奇異向量
- [ ] smoothed L1 penalty 平滑的L1範數懲罰
- [ ] Smoothed topographic L1 sparsity penalty 平滑地形L1稀疏懲罰函式
- [ ] smoothing 平滑
- [ ] Softmax Regresson Softmax迴歸
- [ ] sorted in decreasing order 降序排列
- [ ] source features 源特徵
- [ ] sparse autoencoder 消減歸一化
- [ ] Sparsity 稀疏性
- [ ] sparsity parameter 稀疏性引數
- [ ] sparsity penalty 稀疏懲罰
- [ ] square function 平方函式
- [ ] squared-error 方差
- [ ] stationary 平穩性(不變性)
- [ ] stationary stochastic process 平穩隨機過程
- [ ] step-size 步長值
- [ ] supervised learning 監督學習
- [ ] symmetric positive semi-definite matrix 對稱半正定矩陣
- [ ] symmetry breaking 對稱失效
- [ ] tanh function 雙曲正切函式
- [ ] the average activation 平均活躍度
- [ ] the derivative checking method 梯度驗證方法
- [ ] the empirical distribution 經驗分佈函式
- [ ] the energy function 能量函式
- [ ] the Lagrange dual 拉格朗日對偶函式
- [ ] the log likelihood 對數似然函式
- [ ] the pixel intensity value 畫素灰度值
- [ ] the rate of convergence 收斂速度
- [ ] topographic cost term 拓撲代價項
- [ ] topographic ordered 拓撲秩序
- [ ] transformation 變換
- [200 ] translation invariant 平移不變性
- [ ] trivial answer 平凡解
- [ ] under-complete basis 不完備基
- [ ] unrolling 組合擴充套件
- [ ] unsupervised learning 無監督學習
- [ ] variance 方差
- [ ] vecotrized implementation 向量化實現
- [ ] vectorization 向量化
- [ ] visual cortex 視覺皮層
- [ ] weight decay 權重衰減
- [ ] weighted average 加權平均值
- [ ] whitening 白化
[ ] zero-mean 均值為零
[ ] Letter A
[ ] Accumulated error backpropagation 累積誤差逆傳播
- [ ] Activation Function 啟用函式
- [ ] Adaptive Resonance Theory/ART 自適應諧振理論
- [ ] Addictive model 加性學習
- [ ] Adversarial Networks 對抗網路
- [ ] Affine Layer 仿射層
- [ ] Affinity matrix 親和矩陣
- [ ] Agent 代理 / 智慧體
- [ ] Algorithm 演算法
- [ ] Alpha-beta pruning α-β剪枝
- [ ] Anomaly detection 異常檢測
- [ ] Approximation 近似
- [ ] Area Under ROC Curve/AUC Roc 曲線下面積
- [ ] Artificial General Intelligence/AGI 通用人工智慧
- [ ] Artificial Intelligence/AI 人工智慧
- [ ] Association analysis 關聯分析
- [ ] Attention mechanism 注意力機制
- [ ] Attribute conditional independence assumption 屬性條件獨立性假設
- [ ] Attribute space 屬性空間
- [ ] Attribute value 屬性值
- [ ] Autoencoder 自編碼器
- [ ] Automatic speech recognition 自動語音識別
- [ ] Automatic summarization 自動摘要
- [ ] Average gradient 平均梯度
[ ] Average-Pooling 平均池化
[ ] Letter B
[ ] Backpropagation Through Time 通過時間的反向傳播
- [ ] Backpropagation/BP 反向傳播
- [ ] Base learner 基學習器
- [ ] Base learning algorithm 基學習演算法
- [ ] Batch Normalization/BN 批量歸一化
- [ ] Bayes decision rule 貝葉斯判定準則
- [250 ] Bayes Model Averaging/BMA 貝葉斯模型平均
- [ ] Bayes optimal classifier 貝葉斯最優分類器
- [ ] Bayesian decision theory 貝葉斯決策論
- [ ] Bayesian network 貝葉斯網路
- [ ] Between-class scatter matrix 類間散度矩陣
- [ ] Bias 偏置 / 偏差
- [ ] Bias-variance decomposition 偏差-方差分解
- [ ] Bias-Variance Dilemma 偏差 – 方差困境
- [ ] Bi-directional Long-Short Term Memory/Bi-LSTM 雙向長短期記憶
- [ ] Binary classification 二分類
- [ ] Binomial test 二項檢驗
- [ ] Bi-partition 二分法
- [ ] Boltzmann machine 玻爾茲曼機
- [ ] Bootstrap sampling 自助取樣法/可重複取樣/有放回取樣
- [ ] Bootstrapping 自助法
[ ] Break-Event Point/BEP 平衡點
[ ] Letter C
[ ] Calibration 校準
- [ ] Cascade-Correlation 級聯相關
- [ ] Categorical attribute 離散屬性
- [ ] Class-conditional probability 類條件概率
- [ ] Classification and regression tree/CART 分類與迴歸樹
- [ ] Classifier 分類器
- [ ] Class-imbalance 類別不平衡
- [ ] Closed -form 閉式
- [ ] Cluster 簇/類/叢集
- [ ] Cluster analysis 聚類分析
- [ ] Clustering 聚類
- [ ] Clustering ensemble 聚類整合
- [ ] Co-adapting 共適應
- [ ] Coding matrix 編碼矩陣
- [ ] COLT 國際學習理論會議
- [ ] Committee-based learning 基於委員會的學習
- [ ] Competitive learning 競爭型學習
- [ ] Component learner 元件學習器
- [ ] Comprehensibility 可解釋性
- [ ] Computation Cost 計算成本
- [ ] Computational Linguistics 計算語言學
- [ ] Computer vision 計算機視覺
- [ ] Concept drift 概念漂移
- [ ] Concept Learning System /CLS 概念學習系統
- [ ] Conditional entropy 條件熵
- [ ] Conditional mutual information 條件互資訊
- [ ] Conditional Probability Table/CPT 條件概率表
- [ ] Conditional random field/CRF 條件隨機場
- [ ] Conditional risk 條件風險
- [ ] Confidence 置信度
- [ ] Confusion matrix 混淆矩陣
- [300 ] Connection weight 連線權
- [ ] Connectionism 連結主義
- [ ] Consistency 一致性/相合性
- [ ] Contingency table 列聯表
- [ ] Continuous attribute 連續屬性
- [ ] Convergence 收斂
- [ ] Conversational agent 會話智慧體
- [ ] Convex quadratic programming 凸二次規劃
- [ ] Convexity 凸性
- [ ] Convolutional neural network/CNN 卷積神經網路
- [ ] Co-occurrence 同現
- [ ] Correlation coefficient 相關係數
- [ ] Cosine similarity 餘弦相似度
- [ ] Cost curve 成本曲線
- [ ] Cost Function 成本函式
- [ ] Cost matrix 成本矩陣
- [ ] Cost-sensitive 成本敏感
- [ ] Cross entropy 交叉熵
- [ ] Cross validation 交叉驗證
- [ ] Crowdsourcing 眾包
- [ ] Curse of dimensionality 維數災難
- [ ] Cut point 截斷點
[ ] Cutting plane algorithm 割平面法
[ ] Letter D
[ ] Data mining 資料探勘
- [ ] Data set 資料集
- [ ] Decision Boundary 決策邊界
- [ ] Decision stump 決策樹樁
- [ ] Decision tree 決策樹/判定樹
- [ ] Deduction 演繹
- [ ] Deep Belief Network 深度信念網路
- [ ] Deep Convolutional Generative Adversarial Network/DCGAN 深度卷積生成對抗網路
- [ ] Deep learning 深度學習
- [ ] Deep neural network/DNN 深度神經網路
- [ ] Deep Q-Learning 深度 Q 學習
- [ ] Deep Q-Network 深度 Q 網路
- [ ] Density estimation 密度估計
- [ ] Density-based clustering 密度聚類
- [ ] Differentiable neural computer 可微分神經計算機
- [ ] Dimensionality reduction algorithm 降維演算法
- [ ] Directed edge 有向邊
- [ ] Disagreement measure 不合度量
- [ ] Discriminative model 判別模型
- [ ] Discriminator 判別器
- [ ] Distance measure 距離度量
- [ ] Distance metric learning 距離度量學習
- [ ] Distribution 分佈
- [ ] Divergence 散度
- [350 ] Diversity measure 多樣性度量/差異性度量
- [ ] Domain adaption 領域自適應
- [ ] Downsampling 下采樣
- [ ] D-separation (Directed separation) 有向分離
- [ ] Dual problem 對偶問題
- [ ] Dummy node 啞結點
- [ ] Dynamic Fusion 動態融合
[ ] Dynamic programming 動態規劃
[ ] Letter E
[ ] Eigenvalue decomposition 特徵值分解
- [ ] Embedding 嵌入
- [ ] Emotional analysis 情緒分析
- [ ] Empirical conditional entropy 經驗條件熵
- [ ] Empirical entropy 經驗熵
- [ ] Empirical error 經驗誤差
- [ ] Empirical risk 經驗風險
- [ ] End-to-End 端到端
- [ ] Energy-based model 基於能量的模型
- [ ] Ensemble learning 整合學習
- [ ] Ensemble pruning 整合修剪
- [ ] Error Correcting Output Codes/ECOC 糾錯輸出碼
- [ ] Error rate 錯誤率
- [ ] Error-ambiguity decomposition 誤差-分歧分解
- [ ] Euclidean distance 歐氏距離
- [ ] Evolutionary computation 演化計算
- [ ] Expectation-Maximization 期望最大化
- [ ] Expected loss 期望損失
- [ ] Exploding Gradient Problem 梯度爆炸問題
- [ ] Exponential loss function 指數損失函式
[ ] Extreme Learning Machine/ELM 超限學習機
[ ] Letter F
[ ] Factorization 因子分解
- [ ] False negative 假負類
- [ ] False positive 假正類
- [ ] False Positive Rate/FPR 假正例率
- [ ] Feature engineering 特徵工程
- [ ] Feature selection 特徵選擇
- [ ] Feature vector 特徵向量
- [ ] Featured Learning 特徵學習
- [ ] Feedforward Neural Networks/FNN 前饋神經網路
- [ ] Fine-tuning 微調
- [ ] Flipping output 翻轉法
- [ ] Fluctuation 震盪
- [ ] Forward stagewise algorithm 前向分步演算法
- [ ] Frequentist 頻率主義學派
- [ ] Full-rank matrix 滿秩矩陣
[400 ] Functional neuron 功能神經元
[ ] Letter G
[ ] Gain ratio 增益率
- [ ] Game theory 博弈論
- [ ] Gaussian kernel function 高斯核函式
- [ ] Gaussian Mixture Model 高斯混合模型
- [ ] General Problem Solving 通用問題求解
- [ ] Generalization 泛化
- [ ] Generalization error 泛化誤差
- [ ] Generalization error bound 泛化誤差上界
- [ ] Generalized Lagrange function 廣義拉格朗日函式
- [ ] Generalized linear model 廣義線性模型
- [ ] Generalized Rayleigh quotient 廣義瑞利商
- [ ] Generative Adversarial Networks/GAN 生成對抗網路
- [ ] Generative Model 生成模型
- [ ] Generator 生成器
- [ ] Genetic Algorithm/GA 遺傳演算法
- [ ] Gibbs sampling 吉布斯取樣
- [ ] Gini index 基尼指數
- [ ] Global minimum 全域性最小
- [ ] Global Optimization 全域性優化
- [ ] Gradient boosting 梯度提升
- [ ] Gradient Descent 梯度下降
- [ ] Graph theory 圖論
[ ] Ground-truth 真相/真實
[ ] Letter H
[ ] Hard margin 硬間隔
- [ ] Hard voting 硬投票
- [ ] Harmonic mean 調和平均
- [ ] Hesse matrix 海塞矩陣
- [ ] Hidden dynamic model 隱動態模型
- [ ] Hidden layer 隱藏層
- [ ] Hidden Markov Model/HMM 隱馬爾可夫模型
- [ ] Hierarchical clustering 層次聚類
- [ ] Hilbert space 希爾伯特空間
- [ ] Hinge loss function 合頁損失函式
- [ ] Hold-out 留出法
- [ ] Homogeneous 同質
- [ ] Hybrid computing 混合計算
- [ ] Hyperparameter 超引數
- [ ] Hypothesis 假設
[ ] Hypothesis test 假設驗證
[ ] Letter I
[ ] ICML 國際機器學習會議
- [450 ] Improved iterative scaling/IIS 改進的迭代尺度法
- [ ] Incremental learning 增量學習
- [ ] Independent and identically distributed/i.i.d. 獨立同分布
- [ ] Independent Component Analysis/ICA 獨立成分分析
- [ ] Indicator function 指示函式
- [ ] Individual learner 個體學習器
- [ ] Induction 歸納
- [ ] Inductive bias 歸納偏好
- [ ] Inductive learning 歸納學習
- [ ] Inductive Logic Programming/ILP 歸納邏輯程式設計
- [ ] Information entropy 資訊熵
- [ ] Information gain 資訊增益
- [ ] Input layer 輸入層
- [ ] Insensitive loss 不敏感損失
- [ ] Inter-cluster similarity 簇間相似度
- [ ] International Conference for Machine Learning/ICML 國際機器學習大會
- [ ] Intra-cluster similarity 簇內相似度
- [ ] Intrinsic value 固有值
- [ ] Isometric Mapping/Isomap 等度量對映
- [ ] Isotonic regression 等分迴歸
[ ] Iterative Dichotomiser 迭代二分器
[ ] Letter K
[ ] Kernel method 核方法
- [ ] Kernel trick 核技巧
- [ ] Kernelized Linear Discriminant Analysis/KLDA 核線性判別分析
- [ ] K-fold cross validation k 折交叉驗證/k 倍交叉驗證
- [ ] K-Means Clustering K – 均值聚類
- [ ] K-Nearest Neighbours Algorithm/KNN K近鄰演算法
- [ ] Knowledge base 知識庫
[ ] Knowledge Representation 知識表徵
[ ] Letter L
[ ] Label space 標記空間
- [ ] Lagrange duality 拉格朗日對偶性
- [ ] Lagrange multiplier 拉格朗日乘子
- [ ] Laplace smoothing 拉普拉斯平滑
- [ ] Laplacian correction 拉普拉斯修正
- [ ] Latent Dirichlet Allocation 隱狄利克雷分佈
- [ ] Latent semantic analysis 潛在語義分析
- [ ] Latent variable 隱變數
- [ ] Lazy learning 懶惰學習
- [ ] Learner 學習器
- [ ] Learning by analogy 類比學習
- [ ] Learning rate 學習率
- [ ] Learning Vector Quantization/LVQ 學習向量量化
- [ ] Least squares regression tree 最小二乘迴歸樹
- [ ] Leave-One-Out/LOO 留一法
- [500 ] linear chain conditional random field 線性鏈條件隨機場
- [ ] Linear Discriminant Analysis/LDA 線性判別分析
- [ ] Linear model 線性模型
- [ ] Linear Regression 線性迴歸
- [ ] Link function 聯絡函式
- [ ] Local Markov property 區域性馬爾可夫性
- [ ] Local minimum 區域性最小
- [ ] Log likelihood 對數似然
- [ ] Log odds/logit 對數機率
- [ ] Logistic Regression Logistic 迴歸
- [ ] Log-likelihood 對數似然
- [ ] Log-linear regression 對數線性迴歸
- [ ] Long-Short Term Memory/LSTM 長短期記憶
[ ] Loss function 損失函式
[ ] Letter M
[ ] Machine translation/MT 機器翻譯
- [ ] Macron-P 巨集查準率
- [ ] Macron-R 巨集查全率
- [ ] Majority voting 絕對多數投票法
- [ ] Manifold assumption 流形假設
- [ ] Manifold learning 流形學習
- [ ] Margin theory 間隔理論
- [ ] Marginal distribution 邊際分佈
- [ ] Marginal independence 邊際獨立性
- [ ] Marginalization 邊際化
- [ ] Markov Chain Monte Carlo/MCMC 馬爾可夫鏈蒙特卡羅方法
- [ ] Markov Random Field 馬爾可夫隨機場
- [ ] Maximal clique 最大團
- [ ] Maximum Likelihood Estimation/MLE 極大似然估計/極大似然法
- [ ] Maximum margin 最大間隔
- [ ] Maximum weighted spanning tree 最大帶權生成樹
- [ ] Max-Pooling 最大池化
- [ ] Mean squared error 均方誤差
- [ ] Meta-learner 元學習器
- [ ] Metric learning 度量學習
- [ ] Micro-P 微查準率
- [ ] Micro-R 微查全率
- [ ] Minimal Description Length/MDL 最小描述長度
- [ ] Minimax game 極小極大博弈
- [ ] Misclassification cost 誤分類成本
- [ ] Mixture of experts 混合專家
- [ ] Momentum 動量
- [ ] Moral graph 道德圖/端正圖
- [ ] Multi-class classification 多分類
- [ ] Multi-document summarization 多文件摘要
- [ ] Multi-layer feedforward neural networks 多層前饋神經網路
- [ ] Multilayer Perceptron/MLP 多層感知器
- [ ] Multimodal learning 多模態學習
- [550 ] Multiple Dimensional Scaling 多維縮放
- [ ] Multiple linear regression 多元線性迴歸
- [ ] Multi-response Linear Regression /MLR 多響應線性迴歸
[ ] Mutual information 互資訊
[ ] Letter N
[ ] Naive bayes 樸素貝葉斯
- [ ] Naive Bayes Classifier 樸素貝葉斯分類器
- [ ] Named entity recognition 命名實體識別
- [ ] Nash equilibrium 納什均衡
- [ ] Natural language generation/NLG 自然語言生成
- [ ] Natural language processing 自然語言處理
- [ ] Negative class 負類
- [ ] Negative correlation 負相關法
- [ ] Negative Log Likelihood 負對數似然
- [ ] Neighbourhood Component Analysis/NCA 近鄰成分分析
- [ ] Neural Machine Translation 神經機器翻譯
- [ ] Neural Turing Machine 神經圖靈機
- [ ] Newton method 牛頓法
- [ ] NIPS 國際神經資訊處理系統會議
- [ ] No Free Lunch Theorem/NFL 沒有免費的午餐定理
- [ ] Noise-contrastive estimation 噪音對比估計
- [ ] Nominal attribute 列名屬性
- [ ] Non-convex optimization 非凸優化
- [ ] Nonlinear model 非線性模型
- [ ] Non-metric distance 非度量距離
- [ ] Non-negative matrix factorization 非負矩陣分解
- [ ] Non-ordinal attribute 無序屬性
- [ ] Non-Saturating Game 非飽和博弈
- [ ] Norm 範數
- [ ] Normalization 歸一化
- [ ] Nuclear norm 核範數
[ ] Numerical attribute 數值屬性
[ ] Letter O
[ ] Objective function 目標函式
- [ ] Oblique decision tree 斜決策樹
- [ ] Occam’s razor 奧卡姆剃刀
- [ ] Odds 機率
- [ ] Off-Policy 離策略
- [ ] One shot learning 一次性學習
- [ ] One-Dependent Estimator/ODE 獨依賴估計
- [ ] On-Policy 在策略
- [ ] Ordinal attribute 有序屬性
- [ ] Out-of-bag estimate 包外估計
- [ ] Output layer 輸出層
- [ ] Output smearing 輸出調製法
- [ ] Overfitting 過擬合/過配
[600 ] Oversampling 過取樣
[ ] Letter P
[ ] Paired t-test 成對 t 檢驗
- [ ] Pairwise 成對型
- [ ] Pairwise Markov property 成對馬爾可夫性
- [ ] Parameter 引數
- [ ] Parameter estimation 引數估計
- [ ] Parameter tuning 調參
- [ ] Parse tree 解析樹
- [ ] Particle Swarm Optimization/PSO 粒子群優化演算法
- [ ] Part-of-speech tagging 詞性標註
- [ ] Perceptron 感知機
- [ ] Performance measure 效能度量
- [ ] Plug and Play Generative Network 即插即用生成網路
- [ ] Plurality voting 相對多數投票法
- [ ] Polarity detection 極性檢測
- [ ] Polynomial kernel function 多項式核函式
- [ ] Pooling 池化
- [ ] Positive class 正類
- [ ] Positive definite matrix 正定矩陣
- [ ] Post-hoc test 後續檢驗
- [ ] Post-pruning 後剪枝
- [ ] potential function 勢函式
- [ ] Precision 查準率/準確率
- [ ] Prepruning 預剪枝
- [ ] Principal component analysis/PCA 主成分分析
- [ ] Principle of multiple explanations 多釋原則
- [ ] Prior 先驗
- [ ] Probability Graphical Model 概率圖模型
- [ ] Proximal Gradient Descent/PGD 近端梯度下降
- [ ] Pruning 剪枝
[ ] Pseudo-label 偽標記
[ ] Letter Q
[ ] Quantized Neural Network 量子化神經網路
- [ ] Quantum computer 量子計算機
- [ ] Quantum Computing 量子計算
[ ] Quasi Newton method 擬牛頓法
[ ] Letter R
[ ] Radial Basis Function/RBF 徑向基函式
- [ ] Random Forest Algorithm 隨機森林演算法
- [ ] Random walk 隨機漫步
- [ ] Recall 查全率/召回率
- [ ] Receiver Operating Characteristic/ROC 受試者工作特徵
- [ ] Rectified Linear Unit/ReLU 線性修正單元
- [650 ] Recurrent Neural Network 迴圈神經網路
- [ ] Recursive neural network 遞迴神經網路
- [ ] Reference model 參考模型
- [ ] Regression 迴歸
- [ ] Regularization 正則化
- [ ] Reinforcement learning/RL 強化學習
- [ ] Representation learning 表徵學習
- [ ] Representer theorem 表示定理
- [ ] reproducing kernel Hilbert space/RKHS 再生核希爾伯特空間
- [ ] Re-sampling 重取樣法
- [ ] Rescaling 再縮放
- [ ] Residual Mapping 殘差對映
- [ ] Residual Network 殘差網路
- [ ] Restricted Boltzmann Machine/RBM 受限玻爾茲曼機
- [ ] Restricted Isometry Property/RIP 限定等距性
- [ ] Re-weighting 重賦權法
- [ ] Robustness 穩健性/魯棒性
- [ ] Root node 根結點
- [ ] Rule Engine 規則引擎
[ ] Rule learning 規則學習
[ ] Letter S
[ ] Saddle point 鞍點
- [ ] Sample space 樣本空間
- [ ] Sampling 取樣
- [ ] Score function 評分函式
- [ ] Self-Driving 自動駕駛
- [ ] Self-Organizing Map/SOM 自組織對映
- [ ] Semi-naive Bayes classifiers 半樸素貝葉斯分類器
- [ ] Semi-Supervised Learning 半監督學習
- [ ] semi-Supervised Support Vector Machine 半監督支援向量機
- [ ] Sentiment analysis 情感分析
- [ ] Separating hyperplane 分離超平面
- [ ] Sigmoid function Sigmoid 函式
- [ ] Similarity measure 相似度度量
- [ ] Simulated annealing 模擬退火
- [ ] Simultaneous localization and mapping 同步定位與地圖構建
- [ ] Singular Value Decomposition 奇異值分解
- [ ] Slack variables 鬆弛變數
- [ ] Smoothing 平滑
- [ ] Soft margin 軟間隔
- [ ] Soft margin maximization 軟間隔最大化
- [ ] Soft voting 軟投票
- [ ] Sparse representation 稀疏表徵
- [ ] Sparsity 稀疏性
- [ ] Specialization 特化
- [ ] Spectral Clustering 譜聚類
- [ ] Speech Recognition 語音識別
- [ ] Splitting variable 切分變數
- [700 ] Squashing function 擠壓函式
- [ ] Stability-plasticity dilemma 可塑性-穩定性困境
- [ ] Statistical learning 統計學習
- [ ] Status feature function 狀態特徵函
- [ ] Stochastic gradient descent 隨機梯度下降
- [ ] Stratified sampling 分層取樣
- [ ] Structural risk 結構風險
- [ ] Structural risk minimization/SRM 結構風險最小化
- [ ] Subspace 子空間
- [ ] Supervised learning 監督學習/有導師學習
- [ ] support vector expansion 支援向量展式
- [ ] Support Vector Machine/SVM 支援向量機
- [ ] Surrogat loss 替代損失
- [ ] Surrogate function 替代函式
- [ ] Symbolic learning 符號學習
- [ ] Symbolism 符號主義
[ ] Synset 同義詞集
[ ] Letter T
[ ] T-Distribution Stochastic Neighbour Embedding/t-SNE T – 分佈隨機近鄰嵌入
- [ ] Tensor 張量
- [ ] Tensor Processing Units/TPU 張量處理單元
- [ ] The least square method 最小二乘法
- [ ] Threshold 閾值
- [ ] Threshold logic unit 閾值邏輯單元
- [ ] Threshold-moving 閾值移動
- [ ] Time Step 時間步驟
- [ ] Tokenization 標記化
- [ ] Training error 訓練誤差
- [ ] Training instance 訓練示例/訓練例
- [ ] Transductive learning 直推學習
- [ ] Transfer learning 遷移學習
- [ ] Treebank 樹庫
- [ ] Tria-by-error 試錯法
- [ ] True negative 真負類
- [ ] True positive 真正類
- [ ] True Positive Rate/TPR 真正例率
- [ ] Turing Machine 圖靈機
[ ] Twice-learning 二次學習
[ ] Letter U
[ ] Underfitting 欠擬合/欠配
- [ ] Undersampling 欠取樣
- [ ] Understandability 可理解性
- [ ] Unequal cost 非均等代價
- [ ] Unit-step function 單位階躍函式
- [ ] Univariate decision tree 單變數決策樹
- [ ] Unsupervised learning 無監督學習/無導師學習
- [ ] Unsupervised layer-wise training 無監督逐層訓練
[ ] Upsampling 上取樣
[ ] Letter V
[ ] Vanishing Gradient Problem 梯度消失問題
- [ ] Variational inference 變分推斷
- [ ] VC Theory VC維理論
- [ ] Version space 版本空間
- [ ] Viterbi algorithm 維特比演算法
[760 ] Von Neumann architecture 馮 · 諾伊曼架構
[ ] Letter W
[ ] Wasserstein GAN/WGAN Wasserstein生成對抗網路
- [ ] Weak learner 弱學習器
- [ ] Weight 權重
- [ ] Weight sharing 權共享
- [ ] Weighted voting 加權投票法
- [ ] Within-class scatter matrix 類內散度矩陣
- [ ] Word embedding 詞嵌入
[ ] Word sense disambiguation 詞義消歧
[ ] Letter Z
[ ] Zero-data learning 零資料學習
[ ] Zero-shot learning 零次學習
[ ] A
[ ] approximations近似值
- [ ] arbitrary隨意的
- [ ] affine仿射的
- [ ] arbitrary任意的
- [ ] amino acid氨基酸
- [ ] amenable經得起檢驗的
- [ ] axiom公理,原則
- [ ] abstract提取
- [ ] architecture架構,體系結構;建造業
- [ ] absolute絕對的
- [ ] arsenal軍火庫
- [ ] assignment分配
- [ ] algebra線性代數
- [ ] asymptotically無症狀的
[ ] appropriate恰當的
[ ] B
[ ] bias偏差
- [ ] brevity簡短,簡潔;短暫
- [800 ] broader廣泛
- [ ] briefly簡短的
[ ] batch批量
[ ] C
[ ] convergence 收斂,集中到一點
- [ ] convex凸的
- [ ] contours輪廓
- [ ] constraint約束
- [ ] constant常理
- [ ] commercial商務的
- [ ] complementarity補充
- [ ] coordinate ascent同等級上升
- [ ] clipping剪下物;剪報;修剪
- [ ] component分量;部件
- [ ] continuous連續的
- [ ] covariance協方差
- [ ] canonical正規的,正則的
- [ ] concave非凸的
- [ ] corresponds相符合;相當;通訊
- [ ] corollary推論
- [ ] concrete具體的事物,實在的東西
- [ ] cross validation交叉驗證
- [ ] correlation相互關係
- [ ] convention約定
- [ ] cluster一簇
- [ ] centroids 質心,形心
- [ ] converge收斂
- [ ] computationally計算(機)的
[ ] calculus計算
[ ] D
[ ] derive獲得,取得
- [ ] dual二元的
- [ ] duality二元性;二象性;對偶性
- [ ] derivation求導;得到;起源
- [ ] denote預示,表示,是…的標誌;意味著,[邏]指稱
- [ ] divergence 散度;發散性
- [ ] dimension尺度,規格;維數
- [ ] dot小圓點
- [ ] distortion變形
- [ ] density概率密度函式
- [ ] discrete離散的
- [ ] discriminative有識別能力的
- [ ] diagonal對角
- [ ] dispersion分散,散開
- [ ] determinant決定因素
[849 ] disjoint不相交的
[ ] E
[ ] encounter遇到
- [ ] ellipses橢圓
- [ ] equality等式
- [ ] extra額外的
- [ ] empirical經驗;觀察
- [ ] ennmerate例舉,計數
- [ ] exceed超過,越出
- [ ] expectation期望
- [ ] efficient生效的
- [ ] endow賦予
- [ ] explicitly清楚的
- [ ] exponential family指數家族
[ ] equivalently等價的
[ ] F
[ ] feasible可行的
- [ ] forary初次嘗試
- [ ] finite有限的,限定的
- [ ] forgo摒棄,放棄
- [ ] fliter過濾
- [ ] frequentist最常發生的
- [ ] forward search前向式搜尋
[ ] formalize使定形
[ ] G
[ ] generalized歸納的
- [ ] generalization概括,歸納;普遍化;判斷(根據不足)
- [ ] guarantee保證;抵押品
- [ ] generate形成,產生
- [ ] geometric margins幾何邊界
- [ ] gap裂口
[ ] generative生產的;有生產力的
[ ] H
[ ] heuristic啟發式的;啟發法;啟發程式
- [ ] hone懷戀;磨
[ ] hyperplane超平面
[ ] L
[ ] initial最初的
- [ ] implement執行
- [ ] intuitive憑直覺獲知的
- [ ] incremental增加的
- [900 ] intercept截距
- [ ] intuitious直覺
- [ ] instantiation例子
- [ ] indicator指示物,指示器
- [ ] interative重複的,迭代的
- [ ] integral積分
- [ ] identical相等的;完全相同的
- [ ] indicate表示,指出
- [ ] invariance不變性,恆定性
- [ ] impose把…強加於
- [ ] intermediate中間的
[ ] interpretation解釋,翻譯
[ ] J
[ ] joint distribution聯合概率
[ ] L
[ ] lieu替代
- [ ] logarithmic對數的,用對數表示的
- [ ] latent潛在的
[ ] Leave-one-out cross validation留一法交叉驗證
[ ] M
[ ] magnitude巨大
- [ ] mapping繪圖,製圖;對映
- [ ] matrix矩陣
- [ ] mutual相互的,共同的
- [ ] monotonically單調的
- [ ] minor較小的,次要的
- [ ] multinomial多項的
[ ] multi-class classification二分類問題
[ ] N
[ ] nasty討厭的
- [ ] notation標誌,註釋
[ ] naïve樸素的
[ ] O
[ ] obtain得到
- [ ] oscillate擺動
- [ ] optimization problem最優化問題
- [ ] objective function目標函式
- [ ] optimal最理想的
- [ ] orthogonal(向量,矩陣等)正交的
- [ ] orientation方向
- [ ] ordinary普通的
[ ] occasionally偶然的
[ ] P
[ ] partial derivative偏導數
- [ ] property性質
- [ ] proportional成比例的
- [ ] primal原始的,最初的
- [ ] permit允許
- [ ] pseudocode虛擬碼
- [ ] permissible可允許的
- [ ] polynomial多項式
- [ ] preliminary預備
- [ ] precision精度
- [ ] perturbation 不安,擾亂
- [ ] poist假定,設想
- [ ] positive semi-definite半正定的
- [ ] parentheses圓括號
- [ ] posterior probability後驗概率
- [ ] plementarity補充
- [ ] pictorially影象的
- [ ] parameterize確定…的引數
- [ ] poisson distribution柏鬆分佈
[ ] pertinent相關的
[ ] Q
[ ] quadratic二次的
- [ ] quantity量,數量;分量
[ ] query疑問的
[ ] R
[ ] regularization使系統化;調整
- [ ] reoptimize重新優化
- [ ] restrict限制;限定;約束
- [ ] reminiscent回憶往事的;提醒的;使人聯想…的(of)
- [ ] remark注意
- [ ] random variable隨機變數
- [ ] respect考慮
- [ ] respectively各自的;分別的
[ ] redundant過多的;冗餘的
[ ] S
[ ] susceptible敏感的
- [ ] stochastic可能的;隨機的
- [ ] symmetric對稱的
- [ ] sophisticated複雜的
- [ ] spurious假的;偽造的
- [ ] subtract減去;減法器
- [ ] simultaneously同時發生地;同步地
- [ ] suffice滿足
- [ ] scarce稀有的,難得的
- [ ] split分解,分離
- [ ] subset子集
- [ ] statistic統計量
- [ ] successive iteratious連續的迭代
- [ ] scale標度
- [ ] sort of有幾分的
[ ] squares平方
[ ] T
[ ] trajectory軌跡
- [ ] temporarily暫時的
- [ ] terminology專用名詞
- [ ] tolerance容忍;公差
- [ ] thumb翻閱
- [ ] threshold閾,臨界
- [ ] theorem定理
[ ] tangent正弦
[ ] U
[ ] unit-length vector單位向量
[ ] V
[ ] valid有效的,正確的
- [ ] variance方差
- [ ] variable變數;變元
- [ ] vocabulary詞彙
[ ] valued經估價的;寶貴的
[ ] W
[1038 ] wrapper包裝
[ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]
- [ ]