Convolutional Neural Networks (CNN)

 In computer vision tasks, such as image classification, object

detection or segmentation, CNNs have achieved state-of-the-art
performance due to their shift-invariant ability to capture
representative patterns.
 The convolution operation is the result of sliding the convolution
kernel across the input matrix of the layer to produce a feature
map which is the input of the next layer.
 As convolution and pooling takes into account spatial relations
between features, convolutional neural networks are ideal for
data with a grid-like structure, such as images.