본문 바로가기

Enginius/Machine Learning

Back-propagation (delta rule)

Back-propagation in neural network (aka delta rule)



The main intuition is to define a delta

$$ \delta_k^l \equiv \frac{C}{z_k^l} $$

and find a recursive backward rule

$$ \delta^l_k = \sum_m ( \delta_m^{l+1} W_{mk}^{l+1}  ) \sigma'(z^l_k). $$


The gradients w.r.t. the learning parameters can be computed from the deltas. 


Gradients of a convolution layer



The gradients of a convolution operation can be computed by convolution with the gradient of a loss function w.r.t. the activation and the rotated convolutional feature map. 


'Enginius > Machine Learning' 카테고리의 다른 글

Recent papers regarding robust learning with noisy labels  (0) 2018.03.26
Causalty란 무엇일까?  (0) 2017.12.30
Deconvolution and Checkerboard Artifacts  (0) 2017.12.22
CapsNet  (0) 2017.12.19
NIPS 2017 - Interpretable ML workshop  (0) 2017.12.19