Question 2LeNet - 5 made extensive use of padding to create valid convolutions, to avoid increasing the number of channels after every convolutional layer. True/False?

LeNet - 5 made extensive use of padding to create valid convolutions, to avoid increasing the number of channels after every convolutional layer. True/False?

What is the purpose of zero-padding in a CNN?Question 11Answera.To prevent the reduction of spatial dimensionsb.  To regularize the network and prevent overfittingc.  To adjust the learning rate during trainingd.None

Question 2In LeNet - 5 we can see that as we get into deeper networks the number of channels increases while the height and width of the volume decreases. True/False?

Which is false?Group of answer choicesOutput of a layer in the residual network is the normal output (i.e, what’s produced after applying a filter and an activation function) + the layers input.Output of a layer in the dense network is the normal output (i.e, what’s produced after applying a filter and an activation function) + the layers input.Output of layer 𝑙 in the dense network will be one of the inputs for layers 𝑖∈(𝑙+1,𝐿) where 𝐿 is the total number of layers.A problem of convolution network is that some features may get extracted earlier in the network, but could be useful later on. However, it is hard to keep track of previous non-modified outputs.

Consider a convolutional neural network model that has three convolution layers. The first layer has 50 filters, the second layer has 100 filters, and the third layer has 200 filters. All convolution layers have stride=2, and the same padding. The input images are 300x400 pixels with RGB channels.What is the feature map size after the third convolution layer?4 points150x200x5075x100x10038x50x200