目录
Three Steps for Deep Learning:
Backpropagation——Forward pass and Backward pass
Introduction of Deep Learning
Three Steps for Deep Learning:
-
define a set of function
决定一个好的function set很关键,即决定network的structure。
Fully Connect Feedforward Network
Deep = Many Hidden Layers
Neural Network运算过程如下图,整个Neural Network的运算就是一连串matrix的运算:
-
goodness of function
- Find a function in function set that minimizes total loss L.
- Find the network parameters θ* that minimize total loss L——Gradient Descent. Gradient Descent过程如下,找到一组好的参数后neural network的training就完成了
-
pick the best function
Backpropagation
——如果要用Gradient Descent的方法train一个neural network,应该怎么做。
-
Gradient Descent:
Backpropagation不是一个和Gradient Descent不同的training的方法,它是Gradient Descent的一个比较有效率的演算法。
-
Backpropagation——Forward pass and Backward pass
李老师视频中有详细讲解Forward pass和Backward pass的计算过程,听视频再复习一下,链接: