brandonnam.log
로그인
brandonnam.log
로그인
Advanced Learning Algorithm 9: Activation Functions
brandon
·
2023년 8월 19일
팔로우
0
ML
0
SupervisedML
목록 보기
18/27
1. Alternatives to Sigmoid Function
Linear Activation function
- aka no activation function, just a straight line.
ReLU
stands for
Rectified Linear Unit
2. Choosing Activation Functions
for hidden layers, we use
ReLU
instead of
sigmoid
.
Sigmoid computation takes longer.
Because of 2 flatted parts in sigmoid, gradient descent may take longer.
Sigmoid for binary classification,
Linear for y = - or + regression,
ReLU for y >= 0 regression.
3. Why do we need activation functions?
linear function of linear function is still a linear function.
Let's say hidden layer units are all linear.
Even if the last output unit is sigmoid, the neural network cannot do what logistic regression model cannot do.
Using linear activation function defeats the purpose of using neural network.
brandon
everything happens for a reason
팔로우
이전 포스트
Advanced Learning Algorithm 8: Neural Network Training
다음 포스트
Advanced Learning Algorithm 10: Multiclass Classification
0개의 댓글
댓글 작성