brandonnam.log
로그인
brandonnam.log
로그인
Advanced Learning Algorithm 12: Back Propagation
brandon
·
2023년 8월 24일
팔로우
0
ML
0
SupervisedML
목록 보기
21/27
1. Computation Graph
Back propagation is basically a process to
find a relationship between cost J function and the parameters
.
It works its way backwards from the result, then finds the derivatives values as it moves backwards.
N (Number of units) + P (Number of parameters)
= the number of steps needed to compute the derivatives.
What derivatives??
brandon
everything happens for a reason
팔로우
이전 포스트
Advanced Learning Algorithms 11: Additional Neural Network Concepts
다음 포스트
Advanced Learning Algorithm 13: Advice for Applying Machine Learning
0개의 댓글
댓글 작성