Before going further, let's put together everything we have learned so far. In the figure following we can see the structure of a basic CNN:
A basic convolutional network with convolutional and fully-connected layers in blue and pooling layers in green
Most CNNs share basic properties. Here are some of them:
- We would typically alternate one or more convolutional layers with one pooling layer. In this way, the convolutional layers can detect features at every level of the receptive field size. The aggregated receptive field size of deeper layers is larger than the ones at the beginning of the network. This allows them to capture more complex features from larger input regions. Let's illustrate this with an example. Imagine that the network uses 3x3 convolutions with stride 1 and 2x2 pooling with stride 2:
- The neurons of the...
