Coursera Deep Learning笔记 一步步实现神经网络
-
公式推导
https://www.cnblogs.com/douzujun/p/13046923.html
https://xienaoban.github.io/posts/12524.html -
代码拆分实现
https://www.cnblogs.com/douzujun/p/10325980.html- Initialize parameters / Define hyperparameters
- Loop for num_iterations:
a. Forward propagation
b. Compute cost function
c. Backward propagation
d. Update parameters (using parameters, and grads from backprop) - Use trained parameters to predict labels
-
实例:用手写神经网络实现识别猫
https://www.cnblogs.com/douzujun/p/10344361.html