BW

Alt+F8

또는

Ctrl+K,F

관련 글

https://sacko.tistory.com/19

http://jaejunyoo.blogspot.com/2017/01/backpropagation.html

https://www.linkedin.com/pulse/gradient-descent-backpropagation-ken-chen

As we know, the loss function is a function of weights and biases. So, its gradient can be calculated by taking its derivative with respect to the weights and the biases, so that we know how much each variable contributes to the total error. However, since the relationship between the weights and the biases in the different layers is sort of iterated and accumulated, it is not an easy task to calculate the gradients with respect to them. And this is where backpropagation comes to the rescue!

If I was asked to describe backpropagation algorithm in one sentence, it would be: propagating the total error backward through the connections in the network layer by layer, calculate the contribution (gradient) of each weight and bias to the total error in every layer, then use gradient descent algorithm to optimize the weights and biases, and eventually minimize the total error of the neural network.

최근 두 분야에서 결과를 얻기위해 노력중인 초보자로써 깨달은 것.

둘 사이엔 공통점이 있다.

요소:딥러닝/ 웨이트트레이닝 순

인풋 : 인풋데이터/ 내 몸뚱아리와 그날의 컨디션(수면,스트레스 등)

과정 : 딥러닝 모델과 옵티마이저 그리고 각종 하이퍼파라미터/ reps * sets * weights (=volume)

결과 : 결과데이터,정답과의 차이(score, distance)/ 근성장 정도, 체지방 감량 정도

인풋을 과정에 넣으면 결과가 나온다.

그러면 과정을 평가해, 피드백한다

과정에 대해 수많은 의견,논문이 존재한다

지난 시도들을 돌아보고 피드백한것을 모아 더 좋은 결과를 내기위해 인풋(과정)을 바꾼다.