| A | |
| Activation Function | 激活函数 |
| Adversarial Networks | 对抗网络 |
| Affine Layer | 仿射层 |
| agent | 代理/智能体 |
| algorithm | 算法 |
| alpha-beta pruning | α-β剪枝 |
| anomaly detection | 异常检测 |
| approximation | 近似 |
AGI | Artificial General Intelligence | 通用人工智能 |
AI | Artificial Intelligence | 人工智能 |
| association analysis | 关联分析 |
| attention mechanism | 注意机制 |
| autoencoder | 自编码器 |
ASR | automatic speech recognition | 自动语音识别 |
| automatic summarization | 自动摘要 |
| average gradient | 平均梯度 |
| Average-Pooling | 平均池化 |
| B | |
BP | backpropagation | 反向传播 |
BPTT | Backpropagation Through Time | 通过时间的反向传播 |
BN | Batch Normalization | 分批标准化 |
| Bayesian network | 贝叶斯网络 |
| Bias-Variance Dilemma | 偏差/方差困境 |
Bi-LSTM | Bi-directional Long-Short Term Memory | 双向长短期记忆 |
| bias | 偏置/偏差 |
| big data | 大数据 |
| Boltzmann machine | 玻尔兹曼机 |
| C | |
CPU | Central Processing Unit | 中央处理器 |
| chunk | 词块 |
| clustering | 聚类 |
| cluster analysis | 聚类分析 |
| co-adapting | 共适应 |
| co-occurrence | 共现 |
| Computation Cost | 计算成本 |
| Computational Linguistics | 计算语言学 |
| computer vision | 计算机视觉 |
| concept drift | 概念漂移 |
CRF | conditional random field | 条件随机域/场 |
| convergence | 收敛 |
CA | conversational agent | 会话代理 |
| convexity | 凸性 |
CNN | convolutional neural network | 卷积神经网络 |
| Cost Function | 成本函数 |
| cross entropy | 交叉熵 |
| D | |
| Decision Boundary | 决策边界 |
| Decision Trees | 决策树 |
DBN | Deep Belief Network | 深度信念网络 |
DCGAN | Deep Convolutional Generative Adversarial Network | 深度卷积生成对抗网络 |
DL | deep learning | 深度学习 |
DNN | deep neural network | 深度神经网络 |
| Deep Q-Learning | 深度Q学习 |
DQN | Deep Q-Network | 深度Q网络 |
DNC | differentiable neural computer | 可微分神经计算机 |
| dimensionality reduction algorithm | 降维算法 |
| discriminative model | 判别模型 |
| discriminator | 判别器 |
| divergence | 散度 |
| domain adaption | 领域自适应 |
| Dropout | |
| Dynamic Fusion | 动态融合 |
| E | |
| Embedding | 嵌入 |
| emotional analysis | 情绪分析 |
| End-to-End | 端到端 |
EM | Expectation-Maximization | 期望最大化 |
| Exploding Gradient Problem | 梯度爆炸问题 |
ELM | Extreme Learning Machine | 超限学习机 |
| F | |
FAIR | Facebook Artificial Intelligence Research | Facebook人工智能研究所 |
| factorization | 因子分解 |
| feature engineering | 特征工程 |
| Featured Learning | 特征学习 |
| Feedforward Neural Networks | 前馈神经网络 |
| G | |
| game theory | 博弈论 |
GMM | Gaussian Mixture Model | 高斯混合模型 |
GA | Genetic Algorithm | 遗传算法 |
| Generalization | 泛化 |
GAN | Generative Adversarial Networks | 生成对抗网络 |
| Generative Model | 生成模型 |
| Generator | 生成器 |
| Global Optimization | 全局优化 |
GNMT | Google Neural Machine Translation | 谷歌神经机器翻译 |
| Gradient Descent | 梯度下降 |
| graph theory | 图论 |
GPU | graphics processing unit | 图形处理单元/图形处理器 |
| H | |
HDM | hidden dynamic model | 隐动态模型 |
| hidden layer | 隐藏层 |
HMM | Hidden Markov Model | 隐马尔可夫模型 |
| hybrid computing | 混合计算 |
| hyperparameter | 超参数 |
| I | |
ICA | Independent Component Analysis | 独立成分分析 |
| input | 输入 |
ICML | International Conference for Machine Learning | 国际机器学习大会 |
| language phenomena | 语言现象 |
| latent dirichlet allocation | 隐含狄利克雷分布 |
| J | |
JSD | Jensen-Shannon Divergence | JS距离 |
| K | |
| K-Means Clustering | K-均值聚类 |
K-NN | K-Nearest Neighbours Algorithm | K-最近邻算法 |
| Knowledge Representation | 知识表征 |
KB | knowledge base | 知识库 |
| L | |
| Latent Dirichlet Allocation | 隐狄利克雷分布 |
LSA | latent semantic analysis | 潜在语义分析 |
| learner | 学习器 |
| Linear Regression | 线性回归 |
| log likelihood | 对数似然 |
| Logistic Regression | Logistic回归 |
LSTM | Long-Short Term Memory | 长短期记忆 |
| loss | 损失 |
| M | |
MT | machine translation | 机器翻译 |
| Max-Pooling | 最大池化 |
| Maximum Likelihood | 最大似然 |
| minimax game | 最小最大博弈 |
| Momentum | 动量 |
MLP | Multilayer Perceptron | 多层感知器 |
| multi-document summarization | 多文档摘要 |
MLP | multi layered perceptron | 多层感知器 |
| multimodal learning | 多模态学习 |
| multiple linear regression | 多元线性回归 |
| N | |
| Naive Bayes Classifier | 朴素贝叶斯分类器 |
| named entity recognition | 命名实体识别 |
| Nash equilibrium | 纳什均衡 |
NLG | natural language generation | 自然语言生成 |
NLP | natural language processing | 自然语言处理 |
NLL | Negative Log Likelihood | 负对数似然 |
NMT | Neural Machine Translation | 神经机器翻译 |
NTM | Neural Turing Machine | 神经图灵机 |
NCE | noise-contrastive estimation | 噪音对比估计 |
| non-convex optimization | 非凸优化 |
| non-negative matrix factorization | 非负矩阵分解 |
| Non-Saturating Game | 非饱和博弈 |
| O | |
| objective function | 目标函数 |
| Off-Policy | 离策略 |
| On-Policy | 在策略 |
| one shot learning | 一次性学习 |
| output | 输出 |
| P | |
| Parameter | 参数 |
| parse tree | 解析树 |
| part-of-speech tagging | 词性标注 |
PSO | Particle Swarm Optimization | 粒子群优化算法 |
| perceptron | 感知器 |
| polarity detection | 极性检测 |
| pooling | 池化 |
PPGN | Plug and Play Generative Network | 即插即用生成网络 |
PCA | principal component analysis | 主成分分析 |
| Probability Graphical Model | 概率图模型 |
| Q | |
QNN | Quantized Neural Network | 量子化神经网络 |
| quantum computer | 量子计算机 |
| Quantum Computing | 量子计算 |
| R | |
RBF | Radial Basis Function | 径向基函数 |
| Random Forest Algorithm | 随机森林算法 |
ReLU | Rectified Linear Unit | 线性修正单元/线性修正函数 |
RNN | Recurrent Neural Network | 循环神经网络 |
| recursive neural network | 递归神经网络 |
RL | reinforcement learning | 强化学习 |
| representation | 表征 |
| representation learning | 表征学习 |
| Residual Mapping | 残差映射 |
| Residual Network | 残差网络 |
RBM | Restricted Boltzmann Machine | 受限玻尔兹曼机 |
| Robot | 机器人 |
| Robustness | 稳健性 |
RE | Rule Engine | 规则引擎 |
| S | |
| saddle point | 鞍点 |
| Self-Driving | 自动驾驶 |
SOM | self organised map | 自组织映射 |
| Semi-Supervised Learning | 半监督学习 |
| sentiment analysis | 情感分析 |
SLAM | simultaneous localization and mapping | 同步定位与地图构建 |
SVD | Singular Value Decomposition | 奇异值分解 |
| Spectral Clustering | 谱聚类 |
| Speech Recognition | 语音识别 |
SGD | stochastic gradient descent | 随机梯度下降 |
| supervised learning | 监督学习 |
SVM | Support Vector Machine | 支持向量机 |
| synset | 同义词集 |
| T | |
t-SNE | T-Distribution Stochastic Neighbour Embedding | T-分布随机近邻嵌入 |
| tensor | 张量 |
TPU | Tensor Processing Units | 张量处理单元 |
| the least square method | 最小二乘法 |
| Threshold | 阙值 |
| Time Step | 时间步骤 |
| tokenization | 标记化 |
| treebank | 树库 |
| transfer learning | 迁移学习 |
| Turing Machine | 图灵机 |
| U | |
| unsupervised learning | 无监督学习 |
| V | |
| Vanishing Gradient Problem | 梯度消失问题 |
VC Theory | Vapnik–Chervonenkis theory | 万普尼克-泽范兰杰斯理论 |
| von Neumann architecture | 冯·诺伊曼架构/结构 |
| W | |
WGAN | Wasserstein GAN | |
W | weight | 权重 |
| word embedding | 词嵌入 |
WSD | word sense disambiguation | 词义消歧 |
| X | |
| Y | |
| Z | |
ZSL | zero-shot learning | 零次学习 |
| zero-data learning | 零数据学习 |
| 0 |