强化学习-常用术语缩写表
📋 强化学习常用术语缩写表
| Abbreviation | Full Name | Translation |
|---|---|---|
| RL | Reinforcement Learning | 强化学习 |
| Supervised Learning | 监督学习 | |
| Training | 训练 | |
| Linear Regression | 线性回归 | |
| Unsupervised Learning | 非监督学习 | |
| Cluster | 聚类 | |
| Transfer Learning | 迁移学习 | |
| GAN | Generative Adversarial Networks | 生成对抗网络 |
| Face Recognition | 人脸识别 | |
| Object Detective | 物体识别 | |
| Accuracy | 准确率 | |
| The Turing Test | 图林测试 | |
| Optimization Problem | 最优化问题 | |
| Policy | 策略 | |
| Evaluation Function | 评价函数 | |
| Model | 模型 | |
| MDP | Markov Decision Process | 马尔可夫决策过程 |
| Policy Iteration | 策略迭代 | |
| DP | Dynamic Programming | 动态规划 |
| Monte Carlo Method | 蒙特卡罗法 | |
| TD | Time Difference | 时间差分 |
| Deep Learning | 深度学习 | |
| Convolution Kernel | 卷积核 | |
| Convolutional Layer | 卷积层 | |
| Pooling Layer | 池化层 | |
| ANN | Artificial Neural Network | 人工神经网络 |
| Activation Function | 激励函数 | |
| CNN | Convolutional Neural Networks | 卷积神经网络 |
| Input Layer | 输入层 | |
| Hidden Layer | 隐藏层 | |
| Output Layer | 输出层 | |
| Normalization | 归一化 | |
| Whitening | 白化 | |
| Embedding | 嵌入 | |
| Preprocessing | 预处理 | |
| OOP | Object Oriented Programming | 面向对象编程 |
| TTS | Text to Speech | 文本到语音 |
| Label | 标签 | |
| Layer | 网络层 | |
| Full Connection Layer | 全连接层 | |
| Convolutional Layer | 卷积层 | |
| Pooling Layer | 池化层 | |
| Recurrent Neural Layer | 循环神经层 | |
| Loss Function | 损失函数 | |
| Cost Function | 代价函数 | |
| MSE Loss | Mean Squared Error Loss | 均方损失函数 |
86

被折叠的 条评论
为什么被折叠?



