In multilayer networks, such as MLP or DBN, the outputs of all neurons of the input layer are connected to each neuron in the hidden layer, so the output will again act as the input to the fully-connected layer. In CNN networks, the connection scheme that defines the convolutional layer is significantly different. The convolutional layer is the main type of layer in CNN, where each neuron is connected to a certain region of the input area called the receptive field.
In a typical CNN architecture, a few convolutional layers are connected in a cascade style, where each layer is followed by a rectified linear unit (ReLU) layer, then a pooling layer, then a few more convolutional layers (+ReLU), then another pooling layer, and so on.
The output from each convolution layer is a set of objects called feature maps that are generated by a single kernel filter. The feature maps can then be used to define a new input to the next layer. Each neuron in a CNN network produces an output followed by an activation threshold, which is proportional to the input and not bound:
As you can see in Figure 2, the pooling layers are usually placed after the convolutional layers. The convolutional region is then divided by a pooling layer into sub-regions. Then, a single representative value is selected using either a max-pooling or average pooling technique to reduce the computational time of subsequent layers.
This way, the robustness of the feature with respect to its spatial position gets increased too. To be more specific, when the image properties, as feature maps, pass through the image, they get smaller and smaller as they progress through the network, but they also typically get deeper and deeper, since more feature maps will be added. At the top of the stack, a regular feedforward neural network is added, just like an MLP, which might compose of a few fully connected layers (+ReLUs), and the final layer outputs the prediction, for example, a softmax layer that outputs estimated class probabilities for a multiclass classification.