4. (15 points) Convolutional neural network. Answer the following questions for a CNN that processes RGB color images with the following input size and two layers. - Input: 256256RGB image - Conv1: 2D convolution, K=99 filters, No=12 output channels, valid mode. - MaxPool1: 2D max pooling, K=44 pool size, horizontal and vertical stride s=2. (a) (5 points) What are the dimensions of the input and the outputs for the first two layers for a mini-batch of 100 images. (b) (5 points) How many parameters are there in the Conv1 and MaxPool1 layers? (c) (5 points) Describe a kernel that can detect the difference of the image in the R and G channel, but ignores the B channel (Assume channel index R=1,G=2 and B=3 )