05 Deep learning神经网络编程基础 计算图 --吴恩达

The computation of a neural network are all organized in terms of a forward path or a forward propagation step in which we compute the output of the neural network followed by a backward pass or a back complication step which we use to compute gradients or compute derivatives .

一、计算图（Computational Graph）

1. 数据结构：有向无环图(DAG)表示计算过程
2. 节点组成：
   • 叶子节点：输入数据/模型参数
   • 中间节点：数学运算（如矩阵乘法、激活函数）
3. 边特征：表示张量流动方向与维度关系

二、正向传播 (Forward Propagation)