数学符号
Symbol | Meaning |
---|---|
矩阵 | |
学习率或步长 | |
计算域 的边界 | |
要近似的通用函数,通常是未知的。 | |
的近似版本 | |
计算区域 | |
连续/理想物理模型 | |
离散物理模型 | |
神经网络参数 | |
时间维度 | |
矢量速度 | |
神经网络输入或空间坐标 | |
神经网络输出 | |
学习目标:基本事实、参考或观察数据 |
重要缩写的摘要
ABbreviation | Meaning |
---|---|
BNN | 贝叶斯神经网络 |
CNN | 卷积神经网络 |
DL | 深度学习 |
GD | 梯度下降 |
MLP | 多层感知机,一种具有全连接层的神经网络 |
NN | 神经网络(通用网络,与 CNN 或 MLP 等网络不同) |
PDE | 偏微分方程 |
PBDL | 基于物理的深度学习 |
SGD | 随机梯度下降 |
数学符号
Symbol | Meaning |
---|---|
matrix | |
learning rate or step size | |
boundary of computational domain | |
generic function to be approximated, typically unknown | |
approximate version of | |
computational domain | |
continuous/ideal physical model | |
discretized physical model, PDE | |
neural network params | |
time dimension | |
vector-valued velocity | |
neural network input or spatial coordinate | |
neural network output | |
learning targets: ground truth, reference or observation data |
重要缩写的摘要
ABbreviation | Meaning |
---|---|
BNN | Bayesian neural network |
CNN | Convolutional neural network |
DL | Deep Learning |
GD | (steepest) Gradient Descent |
MLP | Multi-Layer Perceptron, a neural network with fully connected layers |
NN | Neural network (a generic one, in contrast to, e.g., a CNN or MLP) |
PDE | Partial Differential Equation |
PBDL | Physics-Based Deep Learning |
SGD | Stochastic Gradient Descent |