What is the 1×1 convolutional layer typically used for?

A 1×1 convolution simply maps an input pixel with all it’s channels to an output pixel, not looking at anything around itself. It is often used to reduce the number of depth channels, since it is often very slow to multiply volumes with extremely large depths. The bottom one is about ~3.7x slower.

What is NIN network?

We propose a novel deep network structure called “Network In Network” (NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input.

What is residual layer?

Understanding a residual block is quite easy. In traditional neural networks, each layer feeds into the next layer. In a network with residual blocks, each layer feeds into the next layer and directly into the layers about 2–3 hops away. That’s it.

What is fully connected layer in CNN?

Fully Connected Layer is simply, feed forward neural networks. Fully Connected Layers form the last few layers in the network. The input to the fully connected layer is the output from the final Pooling or Convolutional Layer, which is flattened and then fed into the fully connected layer.

What is average pooling layer?

A 2-D average pooling layer performs downsampling by dividing the input into rectangular pooling regions, then computing the average values of each region. Pooling layers follow the convolutional layers for down-sampling, hence, reducing the number of connections to the following layers.

How many parameters does GoogleNet have?

seven million parameters
GoogleNet possesses seven million parameters and contains nine inception modules, four convolutional layers, four max-pooling layers, three average pooling layers, five fully-connected layers, and three softmax layers for the main auxiliary classifiers in the network [33].