2.1 Introduction2.2 The convolutional operation2.3 Relationships between input dimension, output dimension, and the filter dimension2.4 Properties of CNNs2.4.1 Sparse connections2.4.2 Receptive fields2.4.3 Parameter sharing2.4.4 Equivariance to translation2.5 Building a CNN2.5.1 Pooling in CNN2.5.2 Building block of CNN2.6 Complete CNN2.6.1 Le-Net architecture2.7 What is the network learning?2.7.1 Visualizing the first layer2.7.2 Saliency maps2.8 Transposed convolution2.9 Applications of CNN2.10 Conclusion and future work