机器学习缩写词汇
- machine learning : 機器學(xué)習(xí)
- deep learning : 深度學(xué)習(xí)
- image processing : 圖像處理
- natural language processing : 自然語言處理
- algorithms : 算法
- training data set : 訓(xùn)練數(shù)據(jù)集
- facial detection : 面部識別
- malware detection : 惡意程序檢測
- adversarial sample : 對抗樣本
- countermeasuring techniques : 防御技術(shù)
- Indiscriminate Attack:非針對性攻擊
- Adversary’s goal:敵手目標(biāo)
- Adversary’s knowledge :敵手知識
- Adversary’s capability:敵手能力
- Attack strategy:攻擊策略
- Gradient Ascent Strategy:梯度下降策略
- Generative Model:生成模型
- Discriminative model:判別模型
- The Direct Gradient:直接梯度法
- Accuracy:準(zhǔn)確率
- Loss:損失值
- White-Box Attack:白盒攻擊
- Blank-Box Attack:黑盒攻擊
- Reconstruction Attack:重建攻擊
- Proactive Defense:主動防御
- Reactive Defense:被動防御
- Reject On Negative Impact:拒絕消極影響
- Stackelberg Games:斯塔克爾伯格博弈
- Defensive Distillation:防御精餾
- Differential Privacy:差分隱私
- Homomorphic Encryption:同態(tài)加密
- Pattern Recognition:模式識別
- RNN, Recurrent Neural Networks:循環(huán)神經(jīng)網(wǎng)絡(luò)
- FNNs(Feed-forward Neural Networks):前向反饋神經(jīng)網(wǎng)絡(luò)
- Convolutional layer:卷積層
- Rectified Linear Units layer,ReLU layer:線性整流層
- Pooling layer :池化層
- Fully-Connected layer:全連接層
- Face Recognition System :面部識別系統(tǒng) (FRS)
- Adversarial Classification : 敵手分類
- Adversarial Learning :對抗學(xué)習(xí)
- try-and-error:試錯
- Causative Attack :誘發(fā)型攻擊
- Security Violation :安全損害
- Integrity Attack :完整性攻擊
- Availability Attack:可用性攻擊
- Privacy Violation Attack :隱私竊取攻擊
- Specificity of an Attack :攻擊的專一性
- Obfuscation Attacks:迷惑攻擊
- Counterintuitive:反直覺
- Poisoning Attack:投毒攻擊
- Centroid:中心值
- Bridge:橋
- Spoofing Attack :欺騙攻擊
- Avoiding Attack:逃避攻擊
- Impersonate Attack:模仿攻擊
- The Least Likely Class:最小相似類
- Inversion Attack:逆向攻擊
- Confidence Values:置信值
- Equation-Solving Attacks:等式求解攻擊
- Model Extraction Attacks:模型提取攻擊
- Arms Race:攻防技術(shù)競賽
- Non-stationary:不平穩(wěn)
- Data Sanitization:數(shù)據(jù)清洗
- Randomized Prediction Games:隨機預(yù)測博弈
- Deep Contractive Networks:深度收縮網(wǎng)絡(luò)
- Crowdsourcing:眾包
- Randomized Response:隨機響應(yīng)
- Logistic Regression:邏輯回歸
- regression analysis:回歸分析
- AR autoregressive 自回歸
- BPTT back propagation through time 通過時間的反向傳播
- BM Boltzmann machine Boltzmann機
- BP back propagation 反向傳播
- BSB brain-state-in-a-box 腦中盒狀態(tài)
- BSS blind source (signal) separation 盲源(信號)分離
- cmm correlation matrix memory 相關(guān)矩陣記憶
- CV cross-validation 交叉驗證
- DFA deterministic finite-state automata 確定有限狀態(tài)自動機
- EKF extended Kalman filter 擴展卡爾曼濾波器
- EM expectation-maximization 期望最大化
- FIR finite-duration impulse response 有限時間沖擊響應(yīng)
- FM frequency-modulated (signal) 頻率調(diào)制(信號)
- GCV generalized cross-validation 廣義交叉驗證
- GHA generalized Hebbian algorithm 廣義Hebb算法
- GSLC generalized sidelobe canceler 廣義旁瓣消除器
- ICA independent-components analysis 獨立分量分析
- Informax maximum mutual information 最大互信息
- Imax variant of Informax 最大互信息的變體
- Imin another variant of Informax 最大互信息的另一個變體
- KSOM kernel self-organizing map 核自組織映射
- KHA kernel Hebbian algorithm 核Hebb算法
- LMS least-mean-square 最小均方
- LR likelihood ratio 似然比
- LS Least-squares 最小二乘
- LS-TD Least-squares, temporal-difference 最小二乘, 時序差分
- LTP long-term potentiation 長期增強
- LTD long-term depression 長期衰減
- LRT Likelihood ratio test 似然比測試
- MAP Maximum a posteriori 最大后驗估計
- MCA minor-components analysis 次分量分析
- MCMC Markov Chain Monte Carlo 馬爾科夫鏈蒙特卡羅
- MDL minimum description length 最小描述長度
- MIMO multiple input multiple output 多輸入多輸出
- ML maximum likelihood 最大似然
- MLP multilayer perceptron 多層感知器
- MRC model reference control 模型參考控制
- NARMA nonlinear autogressive moving average 非線性自回歸滑動平均
- NARX nonlinear autogressive with exogenous inputs 具有外部輸入的非線性自回歸
- NDP neuro-dynamic programming 神經(jīng)動態(tài)規(guī)劃
- NW Nadaraya-Watson (estimator) Nadaraya-Watson(估計器)
- NWKR Nadaraya-Waston kernel regression Nadaraya-Wastion 核回歸
- OBD optimal brain damage 最優(yōu)腦損傷
- OBS optimal brain surgeon 最優(yōu)腦外傷
- OCR optical character recognition 光學(xué)字符識別
- PAC probably approximately correct 可能近似正確
- PCA principal-components analysis 主分量分析
- PF Particle Filter 粒子濾波器
- pdf probability density function 概率密度函數(shù)
- pmf probability mass function 概率質(zhì)量函數(shù)
- QP quadratic programming 二次規(guī)劃
- RBF radial basis function 徑向基函數(shù)
- RLS recursive least-squares 遞歸最小二乘
- RLS regularized least-squares 正則最小二乘
- RMLP recurrent multilayer preceptron 遞歸多層感知器
- RTRL real-time recurrent learning 實時遞歸學(xué)習(xí)
- SIMO single input multiple output 單輸入多輸出
- SIR sequential importance resampling 逐次重要重采樣
- SIS sequential important sampling 逐次重要采樣
- SISO single input single output 單輸入單輸出
- SNR signal-to-noise ratio 信噪比
- SOM self-organizing map 自組織映射
- SRN simple recurrent network(also referred to as Elman’s recurrent network) 簡單遞歸網(wǎng)絡(luò)(也稱為Elman遞歸網(wǎng)絡(luò))
- SVD singular value decomposition 奇異值分解
- SVM support vector machine 支持向量機
- TD temporal difference 時序差分
- TDNN time-delay neural network 時延神經(jīng)網(wǎng)絡(luò)
- TLFN time-lagged feedforward network 時間滯后前饋網(wǎng)絡(luò)
- VC Vapnik-Chervononkis(dimension) Vapnik-Chervononkis(維數(shù))
- VLSI very-large-scale integration 超大規(guī)模集成
- XOR exclusive OR 異或
總結(jié)
- 上一篇: UG NX 12零件工程图基础
- 下一篇: 华为手机fastboot解锁