Which is of the following represents a correct architectural representation of Convolutional Neural Networks?

Input Layer $->$ Convolution Layer $->$ Pooling $->$ Prediction $->$ Fully Connected Layer $->$ Flatten

Input Layer $->$ Convolution Layer $->$ Pooling $->$ Fully Connected Layer $->$ Flatten

Flatten $->$ Input Layer $->$ Convolution Layer $->$ Pooling $->$ Fully Connected Layer

Input Layer $->$ Convolution Layer $->$ Pooling $->$ Flatten$->$ Fully Connected Layer