簡單理解ConvNet層的Backpropagation

這裏只談一下二維的情況，也就是channel = 1, strides = 1的情況下，單就這一層的計算. ConvNet forward propagation filter’s shape: [height, length, 1] y i , j = Σ n = 0 l e n g t h Σ m = 0 h e i g h t W m , n x i + m , j + n y_{i,j}

>>阅读原文<<