反向传播如何在卷积神经网络(CNN)中工作? [英] How backpropagation works in Convolutional Neural Network(CNN)?

问题描述

我对CNN几乎没有疑问.在下图S2和C3之间，使用了5 * 5大小的内核.

I have few question regarding CNN. In the figure below between Layer S2 and C3, 5*5 sized kernel has been used.

Q1.在那里使用了多少个内核?这些内核中的每一个是否都与S2层中的每个特征图相关?

Q2.使用最大池化时，在反向传播时会出错，即最大池化特征/神经元如何知道/确定其上一个直接层中的哪个(特征图/神经元)是最大值?

Q3.如果要训练内核，那么我们将使用随机值进行初始化，是否有任何公式使用反向传播的误差值来更新这些内核值?

Q4.在上图中，从F6层获取错误后，反向传播如何在输入"和"C5"层之间工作?

Q1. How many kernel has been used there? Do each of these kernel connected with each of the feature map in Layer S2 ?

Q2. When using Max-pooling, while backpropageting error how a max-pooling feature/neuron knows/determines from which (feature map/neuron) in its previous immediate layer it got the max value ?

Q3. If we want to train kernel then we initialize with random value, is there any equation to update these kernel values using backpropagated error value ?

Q4. In the above figure how the backpropagation works between 'Input' and 'C5' layer after getting error from Layer F6 ?

推荐答案

第一季度: C1-> 6个内核 C3-> 16个内核

Q1: C1 -> 6 Kernels C3 -> 16 Kernels

S2和S4只是二次采样，这意味着2 * 2像素将减少到1像素 最受欢迎的池化机制是MAX池化:

S2 and S4 are just subsampling, this means 2*2 Pixel will be decreased to 1 Pixel The most populare Pooling Mechanism is the MAX Pooling:

 (  5   10 ) -->
 (         ) -->  (10)
 (  7    8 ) --> 

第二季度: 您可以保存信息，或者您有足够的时间重新运行max_pooling并检查最大值，然后将错误放在此位置.此2 * 2块中的其他值为零

Q2: You can save the information or if you have enough time re-run the max_pooling and check where the maximum is and then put the error at this position. The other values in this 2*2 Block are zero

这篇关于反向传播如何在卷积神经网络(CNN)中工作?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！